比较提交
合并到: unity-tech-cn:main
unity-tech-cn:/main
unity-tech-cn:/develop-generalizationTraining-TrainerController
unity-tech-cn:/tag-0.2.0
unity-tech-cn:/tag-0.2.1
unity-tech-cn:/tag-0.2.1a
unity-tech-cn:/tag-0.2.1c
unity-tech-cn:/tag-0.2.1d
unity-tech-cn:/hotfix-v0.9.2a
unity-tech-cn:/develop-gpu-test
unity-tech-cn:/0.10.1
unity-tech-cn:/develop-pyinstaller
unity-tech-cn:/develop-horovod
unity-tech-cn:/PhysXArticulations20201
unity-tech-cn:/importdocfix
unity-tech-cn:/develop-resizetexture
unity-tech-cn:/hh-develop-walljump_bugfixes
unity-tech-cn:/develop-walljump-fix-sac
unity-tech-cn:/hh-develop-walljump_rnd
unity-tech-cn:/tag-0.11.0.dev0
unity-tech-cn:/develop-pytorch
unity-tech-cn:/tag-0.11.0.dev2
unity-tech-cn:/develop-newnormalization
unity-tech-cn:/tag-0.11.0.dev3
unity-tech-cn:/develop
unity-tech-cn:/release-0.12.0
unity-tech-cn:/tag-0.12.0-dev
unity-tech-cn:/tag-0.12.0.dev0
unity-tech-cn:/tag-0.12.1
unity-tech-cn:/2D-explorations
unity-tech-cn:/asymm-envs
unity-tech-cn:/tag-0.12.1.dev0
unity-tech-cn:/2D-exploration-raycast
unity-tech-cn:/tag-0.12.1.dev1
unity-tech-cn:/release-0.13.0
unity-tech-cn:/release-0.13.1
unity-tech-cn:/plugin-proof-of-concept
unity-tech-cn:/release-0.14.0
unity-tech-cn:/hotfix-bump-version-master
unity-tech-cn:/soccer-fives
unity-tech-cn:/release-0.14.1
unity-tech-cn:/bug-failed-api-check
unity-tech-cn:/test-recurrent-gail
unity-tech-cn:/hh-add-icons
unity-tech-cn:/release-0.15.0
unity-tech-cn:/release-0.15.1
unity-tech-cn:/hh-develop-all-posed-characters
unity-tech-cn:/internal-policy-ghost
unity-tech-cn:/distributed-training
unity-tech-cn:/hh-develop-improve_tennis
unity-tech-cn:/test-tf-ver
unity-tech-cn:/release_1_branch
unity-tech-cn:/tennis-time-horizon
unity-tech-cn:/whitepaper-experiments
unity-tech-cn:/r2v-yamato-linux
unity-tech-cn:/docs-update
unity-tech-cn:/release_2_branch
unity-tech-cn:/exp-mede
unity-tech-cn:/sensitivity
unity-tech-cn:/release_2_verified_load_fix
unity-tech-cn:/test-sampler
unity-tech-cn:/release_2_verified
unity-tech-cn:/hh-develop-ragdoll-testing
unity-tech-cn:/origin-develop-taggedobservations
unity-tech-cn:/MLA-1734-demo-provider
unity-tech-cn:/sampler-refactor-copy
unity-tech-cn:/PhysXArticulations20201Package
unity-tech-cn:/tag-com.unity.ml-agents_1.0.8
unity-tech-cn:/release_3_branch
unity-tech-cn:/github-actions
unity-tech-cn:/release_3_distributed
unity-tech-cn:/fix-batch-tennis
unity-tech-cn:/distributed-ppo-sac
unity-tech-cn:/gridworld-custom-obs
unity-tech-cn:/hw20-segmentation
unity-tech-cn:/hh-develop-gamedev-demo
unity-tech-cn:/active-variablespeed
unity-tech-cn:/release_4_branch
unity-tech-cn:/fix-env-step-loop
unity-tech-cn:/release_5_branch
unity-tech-cn:/fix-walker
unity-tech-cn:/release_6_branch
unity-tech-cn:/hh-32-observation-crawler
unity-tech-cn:/trainer-plugin
unity-tech-cn:/hh-develop-max-steps-demo-recorder
unity-tech-cn:/hh-develop-loco-walker-variable-speed
unity-tech-cn:/exp-0002
unity-tech-cn:/experiment-less-max-step
unity-tech-cn:/hh-develop-hallway-wall-mesh-fix
unity-tech-cn:/release_7_branch
unity-tech-cn:/exp-vince
unity-tech-cn:/hh-develop-gridsensor-tests
unity-tech-cn:/tag-release_8_test0
unity-tech-cn:/tag-release_8_test1
unity-tech-cn:/release_8_branch
unity-tech-cn:/docfix-end-episode
unity-tech-cn:/release_9_branch
unity-tech-cn:/hybrid-action-rewardsignals
unity-tech-cn:/MLA-462-yamato-win
unity-tech-cn:/exp-alternate-atten
unity-tech-cn:/hh-develop-fps_game_project
unity-tech-cn:/fix-conflict-base-env
unity-tech-cn:/release_10_branch
unity-tech-cn:/exp-bullet-hell-trainer
unity-tech-cn:/ai-summit-exp
unity-tech-cn:/comms-grad
unity-tech-cn:/walljump-pushblock
unity-tech-cn:/goal-conditioning
unity-tech-cn:/release_11_branch
unity-tech-cn:/hh-develop-water-balloon-fight
unity-tech-cn:/gc-hyper
unity-tech-cn:/layernorm
unity-tech-cn:/yamato-linux-debug-venv
unity-tech-cn:/soccer-comms
unity-tech-cn:/hh-develop-pushblockcollab
unity-tech-cn:/release_12_branch
unity-tech-cn:/fix-get-step-sp-curr
unity-tech-cn:/continuous-comms
unity-tech-cn:/no-comms
unity-tech-cn:/hh-develop-zombiepushblock
unity-tech-cn:/hypernetwork
unity-tech-cn:/revert-4859-develop-update-readme
unity-tech-cn:/sequencer-env-attention
unity-tech-cn:/hh-develop-variableobs
unity-tech-cn:/exp-tanh
unity-tech-cn:/reward-dist
unity-tech-cn:/exp-weight-decay
unity-tech-cn:/exp-robot
unity-tech-cn:/bullet-hell-barracuda-test-1.3.1
unity-tech-cn:/release_13_branch
unity-tech-cn:/release_14_branch
unity-tech-cn:/exp-clipped-gaussian-entropy
unity-tech-cn:/tic-tac-toe
unity-tech-cn:/hh-develop-dodgeball
unity-tech-cn:/repro-vis-obs-perf
unity-tech-cn:/v2-staging-rebase
unity-tech-cn:/release_15_branch
unity-tech-cn:/release_15_removeendepisode
unity-tech-cn:/release_16_branch
unity-tech-cn:/release_16_fix_gridsensor
unity-tech-cn:/ai-hw-2021
unity-tech-cn:/check-for-ModelOverriders
unity-tech-cn:/fix-grid-obs-shape-init
unity-tech-cn:/fix-gym-needs-reset
unity-tech-cn:/fix-resume-imi
unity-tech-cn:/release_17_branch
unity-tech-cn:/release_17_branch_gpu_test
unity-tech-cn:/colab-links
unity-tech-cn:/exp-continuous-div
unity-tech-cn:/release_17_branch_gpu_2
unity-tech-cn:/exp-diverse-behavior
unity-tech-cn:/grid-onehot-extra-dim-empty
unity-tech-cn:/2.0-verified
unity-tech-cn:/faster-entropy-coeficient-convergence
unity-tech-cn:/pre-r18-update-changelog
unity-tech-cn:/release_18_branch
unity-tech-cn:/main/tracking
unity-tech-cn:/main/reward-providers
unity-tech-cn:/main/project-upgrade
unity-tech-cn:/main/limitation-docs
unity-tech-cn:/develop/nomaxstep-test
unity-tech-cn:/develop/tf2.0
unity-tech-cn:/develop/tanhsquash
unity-tech-cn:/develop/magic-string
unity-tech-cn:/develop/trainerinterface
unity-tech-cn:/develop/separatevalue
unity-tech-cn:/develop/nopreviousactions
unity-tech-cn:/develop/reenablerepeatactions
unity-tech-cn:/develop/0memories
unity-tech-cn:/develop/fixmemoryleak
unity-tech-cn:/develop/reducewalljump
unity-tech-cn:/develop/removeactionholder-onehot
unity-tech-cn:/develop/canonicalize-quaternions
unity-tech-cn:/develop/self-playassym
unity-tech-cn:/develop/demo-load-seek
unity-tech-cn:/develop/progress-bar
unity-tech-cn:/develop/sac-apex
unity-tech-cn:/develop/cubewars
unity-tech-cn:/develop/add-fire
unity-tech-cn:/develop/gym-wrapper
unity-tech-cn:/develop/mm-docs-main-readme
unity-tech-cn:/develop/mm-docs-overview
unity-tech-cn:/develop/no-threading
unity-tech-cn:/develop/dockerfile
unity-tech-cn:/develop/model-store
unity-tech-cn:/develop/checkout-conversion-rebase
unity-tech-cn:/develop/model-transfer
unity-tech-cn:/develop/bisim-review
unity-tech-cn:/develop/taggedobservations
unity-tech-cn:/develop/transfer-bisim
unity-tech-cn:/develop/bisim-sac-transfer
unity-tech-cn:/develop/basketball
unity-tech-cn:/develop/torchmodules
unity-tech-cn:/develop/fixmarkdown
unity-tech-cn:/develop/shortenstrikervsgoalie
unity-tech-cn:/develop/shortengoalie
unity-tech-cn:/develop/torch-save-rp
unity-tech-cn:/develop/torch-to-np
unity-tech-cn:/develop/torch-omp-no-thread
unity-tech-cn:/develop/actionmodel-csharp
unity-tech-cn:/develop/torch-extra
unity-tech-cn:/develop/restructure-torch-networks
unity-tech-cn:/develop/jit
unity-tech-cn:/develop/adjust-cpu-settings-experiment
unity-tech-cn:/develop/torch-sac-threading
unity-tech-cn:/develop/wb
unity-tech-cn:/develop/amrl
unity-tech-cn:/develop/memorydump
unity-tech-cn:/develop/permutepytorch
unity-tech-cn:/develop/sac-targetq
unity-tech-cn:/develop/actions-out
unity-tech-cn:/develop/reshapeonnxmemories
unity-tech-cn:/develop/crawlergail
unity-tech-cn:/develop/debugtorchfood
unity-tech-cn:/develop/hybrid-actions
unity-tech-cn:/develop/bullet-hell
unity-tech-cn:/develop/action-spec-gym
unity-tech-cn:/develop/battlefoodcollector
unity-tech-cn:/develop/use-action-buffers
unity-tech-cn:/develop/hardswish
unity-tech-cn:/develop/leakyrelu
unity-tech-cn:/develop/torch-clip-scale
unity-tech-cn:/develop/contentropy
unity-tech-cn:/develop/manch
unity-tech-cn:/develop/torchcrawlerdebug
unity-tech-cn:/develop/fix-nan
unity-tech-cn:/develop/multitype-buffer
unity-tech-cn:/develop/windows-delay
unity-tech-cn:/develop/torch-tanh
unity-tech-cn:/develop/gail-norm
unity-tech-cn:/develop/multiprocess
unity-tech-cn:/develop/unified-obs
unity-tech-cn:/develop/rm-rf-new-models
unity-tech-cn:/develop/skipcritic
unity-tech-cn:/develop/centralizedcritic
unity-tech-cn:/develop/dodgeball-tests
unity-tech-cn:/develop/cc-teammanager
unity-tech-cn:/develop/weight-decay
unity-tech-cn:/develop/singular-embeddings
unity-tech-cn:/develop/zombieteammanager
unity-tech-cn:/develop/superpush
unity-tech-cn:/develop/teammanager
unity-tech-cn:/develop/zombie-exp
unity-tech-cn:/develop/update-readme
unity-tech-cn:/develop/readme-fix
unity-tech-cn:/develop/coma-noact
unity-tech-cn:/develop/coma-withq
unity-tech-cn:/develop/coma2
unity-tech-cn:/develop/action-slice
unity-tech-cn:/develop/gru
unity-tech-cn:/develop/critic-op-lstm-currentmem
unity-tech-cn:/develop/decaygail
unity-tech-cn:/develop/gail-srl-hack
unity-tech-cn:/develop/rear-pad
unity-tech-cn:/develop/mm-copyright-dates
unity-tech-cn:/develop/dodgeball-raycasts
unity-tech-cn:/develop/collab-envs-exp-ervin
unity-tech-cn:/develop/pushcollabonly
unity-tech-cn:/develop/sample-curation
unity-tech-cn:/develop/soccer-groupman
unity-tech-cn:/develop/input-actuator-tanks
unity-tech-cn:/develop/validate-release-fix
unity-tech-cn:/develop/new-console-log
unity-tech-cn:/develop/lex-walker-model
unity-tech-cn:/develop/lstm-burnin
unity-tech-cn:/develop/grid-vaiable-names
unity-tech-cn:/develop/fix-attn-embedding
unity-tech-cn:/develop/api-documentation-update-some-fixes
unity-tech-cn:/develop/update-grpc
unity-tech-cn:/develop/grid-rootref-debug
unity-tech-cn:/develop/pbcollab-rays
unity-tech-cn:/develop/2.0-verified-pre
unity-tech-cn:/develop/parameterizedenvs
unity-tech-cn:/develop/custom-ray-sensor
unity-tech-cn:/develop/mm-add-v2blog
unity-tech-cn:/develop/custom-raycast
unity-tech-cn:/develop/area-manager
unity-tech-cn:/develop/remove-unecessary-lr
unity-tech-cn:/develop/use-base-env-in-learn
unity-tech-cn:/soccer-fives/multiagent
unity-tech-cn:/develop/cubewars/splashdamage
unity-tech-cn:/develop/add-fire/exp
unity-tech-cn:/develop/add-fire/jit
unity-tech-cn:/develop/add-fire/speedtest
unity-tech-cn:/develop/add-fire/bc
unity-tech-cn:/develop/add-fire/ckpt-2
unity-tech-cn:/develop/add-fire/normalize-context
unity-tech-cn:/develop/add-fire/components-dir
unity-tech-cn:/develop/add-fire/halfentropy
unity-tech-cn:/develop/add-fire/memoryclass
unity-tech-cn:/develop/add-fire/categoricaldist
unity-tech-cn:/develop/add-fire/mm
unity-tech-cn:/develop/add-fire/sac-lst
unity-tech-cn:/develop/add-fire/mm3
unity-tech-cn:/develop/add-fire/continuous
unity-tech-cn:/develop/add-fire/ghost
unity-tech-cn:/develop/add-fire/policy-tests
unity-tech-cn:/develop/add-fire/export-discrete
unity-tech-cn:/develop/add-fire/test-simple-rl-fix-resnet
unity-tech-cn:/develop/add-fire/remove-currdoc
unity-tech-cn:/develop/add-fire/clean2
unity-tech-cn:/develop/add-fire/doc-cleanups
unity-tech-cn:/develop/add-fire/changelog
unity-tech-cn:/develop/add-fire/mm2
unity-tech-cn:/develop/model-transfer/add-physics
unity-tech-cn:/develop/model-transfer/train
unity-tech-cn:/develop/jit/experiments
unity-tech-cn:/exp-vince/sep30-2020
unity-tech-cn:/hh-develop-gridsensor-tests/static
unity-tech-cn:/develop/hybrid-actions/distlist
unity-tech-cn:/develop/bullet-hell/buffer
unity-tech-cn:/goal-conditioning/new
unity-tech-cn:/goal-conditioning/sensors-2
unity-tech-cn:/goal-conditioning/sensors-3-pytest-fix
unity-tech-cn:/goal-conditioning/grid-world
unity-tech-cn:/soccer-comms/disc
unity-tech-cn:/develop/centralizedcritic/counterfact
unity-tech-cn:/develop/centralizedcritic/mm
unity-tech-cn:/develop/centralizedcritic/nonego
unity-tech-cn:/develop/zombieteammanager/disableagent
unity-tech-cn:/develop/zombieteammanager/killfirst
unity-tech-cn:/develop/superpush/int
unity-tech-cn:/develop/superpush/branch-cleanup
unity-tech-cn:/develop/teammanager/int
unity-tech-cn:/develop/teammanager/cubewar-nocycle
unity-tech-cn:/develop/teammanager/cubewars
unity-tech-cn:/develop/superpush/int/hunter
unity-tech-cn:/goal-conditioning/new/allo-crawler
unity-tech-cn:/develop/coma2/clip
unity-tech-cn:/develop/coma2/singlenetwork
unity-tech-cn:/develop/coma2/samenet
unity-tech-cn:/develop/coma2/fixgroup
unity-tech-cn:/develop/coma2/samenet/sum
unity-tech-cn:/hh-develop-dodgeball/goy-input
unity-tech-cn:/develop/soccer-groupman/mod
unity-tech-cn:/develop/soccer-groupman/mod/hunter
unity-tech-cn:/develop/soccer-groupman/mod/hunter/cine
unity-tech-cn:/ai-hw-2021/tensor-applier
拉取从: unity-tech-cn:develop/teammanager/int
unity-tech-cn:/main
unity-tech-cn:/develop-generalizationTraining-TrainerController
unity-tech-cn:/tag-0.2.0
unity-tech-cn:/tag-0.2.1
unity-tech-cn:/tag-0.2.1a
unity-tech-cn:/tag-0.2.1c
unity-tech-cn:/tag-0.2.1d
unity-tech-cn:/hotfix-v0.9.2a
unity-tech-cn:/develop-gpu-test
unity-tech-cn:/0.10.1
unity-tech-cn:/develop-pyinstaller
unity-tech-cn:/develop-horovod
unity-tech-cn:/PhysXArticulations20201
unity-tech-cn:/importdocfix
unity-tech-cn:/develop-resizetexture
unity-tech-cn:/hh-develop-walljump_bugfixes
unity-tech-cn:/develop-walljump-fix-sac
unity-tech-cn:/hh-develop-walljump_rnd
unity-tech-cn:/tag-0.11.0.dev0
unity-tech-cn:/develop-pytorch
unity-tech-cn:/tag-0.11.0.dev2
unity-tech-cn:/develop-newnormalization
unity-tech-cn:/tag-0.11.0.dev3
unity-tech-cn:/develop
unity-tech-cn:/release-0.12.0
unity-tech-cn:/tag-0.12.0-dev
unity-tech-cn:/tag-0.12.0.dev0
unity-tech-cn:/tag-0.12.1
unity-tech-cn:/2D-explorations
unity-tech-cn:/asymm-envs
unity-tech-cn:/tag-0.12.1.dev0
unity-tech-cn:/2D-exploration-raycast
unity-tech-cn:/tag-0.12.1.dev1
unity-tech-cn:/release-0.13.0
unity-tech-cn:/release-0.13.1
unity-tech-cn:/plugin-proof-of-concept
unity-tech-cn:/release-0.14.0
unity-tech-cn:/hotfix-bump-version-master
unity-tech-cn:/soccer-fives
unity-tech-cn:/release-0.14.1
unity-tech-cn:/bug-failed-api-check
unity-tech-cn:/test-recurrent-gail
unity-tech-cn:/hh-add-icons
unity-tech-cn:/release-0.15.0
unity-tech-cn:/release-0.15.1
unity-tech-cn:/hh-develop-all-posed-characters
unity-tech-cn:/internal-policy-ghost
unity-tech-cn:/distributed-training
unity-tech-cn:/hh-develop-improve_tennis
unity-tech-cn:/test-tf-ver
unity-tech-cn:/release_1_branch
unity-tech-cn:/tennis-time-horizon
unity-tech-cn:/whitepaper-experiments
unity-tech-cn:/r2v-yamato-linux
unity-tech-cn:/docs-update
unity-tech-cn:/release_2_branch
unity-tech-cn:/exp-mede
unity-tech-cn:/sensitivity
unity-tech-cn:/release_2_verified_load_fix
unity-tech-cn:/test-sampler
unity-tech-cn:/release_2_verified
unity-tech-cn:/hh-develop-ragdoll-testing
unity-tech-cn:/origin-develop-taggedobservations
unity-tech-cn:/MLA-1734-demo-provider
unity-tech-cn:/sampler-refactor-copy
unity-tech-cn:/PhysXArticulations20201Package
unity-tech-cn:/tag-com.unity.ml-agents_1.0.8
unity-tech-cn:/release_3_branch
unity-tech-cn:/github-actions
unity-tech-cn:/release_3_distributed
unity-tech-cn:/fix-batch-tennis
unity-tech-cn:/distributed-ppo-sac
unity-tech-cn:/gridworld-custom-obs
unity-tech-cn:/hw20-segmentation
unity-tech-cn:/hh-develop-gamedev-demo
unity-tech-cn:/active-variablespeed
unity-tech-cn:/release_4_branch
unity-tech-cn:/fix-env-step-loop
unity-tech-cn:/release_5_branch
unity-tech-cn:/fix-walker
unity-tech-cn:/release_6_branch
unity-tech-cn:/hh-32-observation-crawler
unity-tech-cn:/trainer-plugin
unity-tech-cn:/hh-develop-max-steps-demo-recorder
unity-tech-cn:/hh-develop-loco-walker-variable-speed
unity-tech-cn:/exp-0002
unity-tech-cn:/experiment-less-max-step
unity-tech-cn:/hh-develop-hallway-wall-mesh-fix
unity-tech-cn:/release_7_branch
unity-tech-cn:/exp-vince
unity-tech-cn:/hh-develop-gridsensor-tests
unity-tech-cn:/tag-release_8_test0
unity-tech-cn:/tag-release_8_test1
unity-tech-cn:/release_8_branch
unity-tech-cn:/docfix-end-episode
unity-tech-cn:/release_9_branch
unity-tech-cn:/hybrid-action-rewardsignals
unity-tech-cn:/MLA-462-yamato-win
unity-tech-cn:/exp-alternate-atten
unity-tech-cn:/hh-develop-fps_game_project
unity-tech-cn:/fix-conflict-base-env
unity-tech-cn:/release_10_branch
unity-tech-cn:/exp-bullet-hell-trainer
unity-tech-cn:/ai-summit-exp
unity-tech-cn:/comms-grad
unity-tech-cn:/walljump-pushblock
unity-tech-cn:/goal-conditioning
unity-tech-cn:/release_11_branch
unity-tech-cn:/hh-develop-water-balloon-fight
unity-tech-cn:/gc-hyper
unity-tech-cn:/layernorm
unity-tech-cn:/yamato-linux-debug-venv
unity-tech-cn:/soccer-comms
unity-tech-cn:/hh-develop-pushblockcollab
unity-tech-cn:/release_12_branch
unity-tech-cn:/fix-get-step-sp-curr
unity-tech-cn:/continuous-comms
unity-tech-cn:/no-comms
unity-tech-cn:/hh-develop-zombiepushblock
unity-tech-cn:/hypernetwork
unity-tech-cn:/revert-4859-develop-update-readme
unity-tech-cn:/sequencer-env-attention
unity-tech-cn:/hh-develop-variableobs
unity-tech-cn:/exp-tanh
unity-tech-cn:/reward-dist
unity-tech-cn:/exp-weight-decay
unity-tech-cn:/exp-robot
unity-tech-cn:/bullet-hell-barracuda-test-1.3.1
unity-tech-cn:/release_13_branch
unity-tech-cn:/release_14_branch
unity-tech-cn:/exp-clipped-gaussian-entropy
unity-tech-cn:/tic-tac-toe
unity-tech-cn:/hh-develop-dodgeball
unity-tech-cn:/repro-vis-obs-perf
unity-tech-cn:/v2-staging-rebase
unity-tech-cn:/release_15_branch
unity-tech-cn:/release_15_removeendepisode
unity-tech-cn:/release_16_branch
unity-tech-cn:/release_16_fix_gridsensor
unity-tech-cn:/ai-hw-2021
unity-tech-cn:/check-for-ModelOverriders
unity-tech-cn:/fix-grid-obs-shape-init
unity-tech-cn:/fix-gym-needs-reset
unity-tech-cn:/fix-resume-imi
unity-tech-cn:/release_17_branch
unity-tech-cn:/release_17_branch_gpu_test
unity-tech-cn:/colab-links
unity-tech-cn:/exp-continuous-div
unity-tech-cn:/release_17_branch_gpu_2
unity-tech-cn:/exp-diverse-behavior
unity-tech-cn:/grid-onehot-extra-dim-empty
unity-tech-cn:/2.0-verified
unity-tech-cn:/faster-entropy-coeficient-convergence
unity-tech-cn:/pre-r18-update-changelog
unity-tech-cn:/release_18_branch
unity-tech-cn:/main/tracking
unity-tech-cn:/main/reward-providers
unity-tech-cn:/main/project-upgrade
unity-tech-cn:/main/limitation-docs
unity-tech-cn:/develop/nomaxstep-test
unity-tech-cn:/develop/tf2.0
unity-tech-cn:/develop/tanhsquash
unity-tech-cn:/develop/magic-string
unity-tech-cn:/develop/trainerinterface
unity-tech-cn:/develop/separatevalue
unity-tech-cn:/develop/nopreviousactions
unity-tech-cn:/develop/reenablerepeatactions
unity-tech-cn:/develop/0memories
unity-tech-cn:/develop/fixmemoryleak
unity-tech-cn:/develop/reducewalljump
unity-tech-cn:/develop/removeactionholder-onehot
unity-tech-cn:/develop/canonicalize-quaternions
unity-tech-cn:/develop/self-playassym
unity-tech-cn:/develop/demo-load-seek
unity-tech-cn:/develop/progress-bar
unity-tech-cn:/develop/sac-apex
unity-tech-cn:/develop/cubewars
unity-tech-cn:/develop/add-fire
unity-tech-cn:/develop/gym-wrapper
unity-tech-cn:/develop/mm-docs-main-readme
unity-tech-cn:/develop/mm-docs-overview
unity-tech-cn:/develop/no-threading
unity-tech-cn:/develop/dockerfile
unity-tech-cn:/develop/model-store
unity-tech-cn:/develop/checkout-conversion-rebase
unity-tech-cn:/develop/model-transfer
unity-tech-cn:/develop/bisim-review
unity-tech-cn:/develop/taggedobservations
unity-tech-cn:/develop/transfer-bisim
unity-tech-cn:/develop/bisim-sac-transfer
unity-tech-cn:/develop/basketball
unity-tech-cn:/develop/torchmodules
unity-tech-cn:/develop/fixmarkdown
unity-tech-cn:/develop/shortenstrikervsgoalie
unity-tech-cn:/develop/shortengoalie
unity-tech-cn:/develop/torch-save-rp
unity-tech-cn:/develop/torch-to-np
unity-tech-cn:/develop/torch-omp-no-thread
unity-tech-cn:/develop/actionmodel-csharp
unity-tech-cn:/develop/torch-extra
unity-tech-cn:/develop/restructure-torch-networks
unity-tech-cn:/develop/jit
unity-tech-cn:/develop/adjust-cpu-settings-experiment
unity-tech-cn:/develop/torch-sac-threading
unity-tech-cn:/develop/wb
unity-tech-cn:/develop/amrl
unity-tech-cn:/develop/memorydump
unity-tech-cn:/develop/permutepytorch
unity-tech-cn:/develop/sac-targetq
unity-tech-cn:/develop/actions-out
unity-tech-cn:/develop/reshapeonnxmemories
unity-tech-cn:/develop/crawlergail
unity-tech-cn:/develop/debugtorchfood
unity-tech-cn:/develop/hybrid-actions
unity-tech-cn:/develop/bullet-hell
unity-tech-cn:/develop/action-spec-gym
unity-tech-cn:/develop/battlefoodcollector
unity-tech-cn:/develop/use-action-buffers
unity-tech-cn:/develop/hardswish
unity-tech-cn:/develop/leakyrelu
unity-tech-cn:/develop/torch-clip-scale
unity-tech-cn:/develop/contentropy
unity-tech-cn:/develop/manch
unity-tech-cn:/develop/torchcrawlerdebug
unity-tech-cn:/develop/fix-nan
unity-tech-cn:/develop/multitype-buffer
unity-tech-cn:/develop/windows-delay
unity-tech-cn:/develop/torch-tanh
unity-tech-cn:/develop/gail-norm
unity-tech-cn:/develop/multiprocess
unity-tech-cn:/develop/unified-obs
unity-tech-cn:/develop/rm-rf-new-models
unity-tech-cn:/develop/skipcritic
unity-tech-cn:/develop/centralizedcritic
unity-tech-cn:/develop/dodgeball-tests
unity-tech-cn:/develop/cc-teammanager
unity-tech-cn:/develop/weight-decay
unity-tech-cn:/develop/singular-embeddings
unity-tech-cn:/develop/zombieteammanager
unity-tech-cn:/develop/superpush
unity-tech-cn:/develop/teammanager
unity-tech-cn:/develop/zombie-exp
unity-tech-cn:/develop/update-readme
unity-tech-cn:/develop/readme-fix
unity-tech-cn:/develop/coma-noact
unity-tech-cn:/develop/coma-withq
unity-tech-cn:/develop/coma2
unity-tech-cn:/develop/action-slice
unity-tech-cn:/develop/gru
unity-tech-cn:/develop/critic-op-lstm-currentmem
unity-tech-cn:/develop/decaygail
unity-tech-cn:/develop/gail-srl-hack
unity-tech-cn:/develop/rear-pad
unity-tech-cn:/develop/mm-copyright-dates
unity-tech-cn:/develop/dodgeball-raycasts
unity-tech-cn:/develop/collab-envs-exp-ervin
unity-tech-cn:/develop/pushcollabonly
unity-tech-cn:/develop/sample-curation
unity-tech-cn:/develop/soccer-groupman
unity-tech-cn:/develop/input-actuator-tanks
unity-tech-cn:/develop/validate-release-fix
unity-tech-cn:/develop/new-console-log
unity-tech-cn:/develop/lex-walker-model
unity-tech-cn:/develop/lstm-burnin
unity-tech-cn:/develop/grid-vaiable-names
unity-tech-cn:/develop/fix-attn-embedding
unity-tech-cn:/develop/api-documentation-update-some-fixes
unity-tech-cn:/develop/update-grpc
unity-tech-cn:/develop/grid-rootref-debug
unity-tech-cn:/develop/pbcollab-rays
unity-tech-cn:/develop/2.0-verified-pre
unity-tech-cn:/develop/parameterizedenvs
unity-tech-cn:/develop/custom-ray-sensor
unity-tech-cn:/develop/mm-add-v2blog
unity-tech-cn:/develop/custom-raycast
unity-tech-cn:/develop/area-manager
unity-tech-cn:/develop/remove-unecessary-lr
unity-tech-cn:/develop/use-base-env-in-learn
unity-tech-cn:/soccer-fives/multiagent
unity-tech-cn:/develop/cubewars/splashdamage
unity-tech-cn:/develop/add-fire/exp
unity-tech-cn:/develop/add-fire/jit
unity-tech-cn:/develop/add-fire/speedtest
unity-tech-cn:/develop/add-fire/bc
unity-tech-cn:/develop/add-fire/ckpt-2
unity-tech-cn:/develop/add-fire/normalize-context
unity-tech-cn:/develop/add-fire/components-dir
unity-tech-cn:/develop/add-fire/halfentropy
unity-tech-cn:/develop/add-fire/memoryclass
unity-tech-cn:/develop/add-fire/categoricaldist
unity-tech-cn:/develop/add-fire/mm
unity-tech-cn:/develop/add-fire/sac-lst
unity-tech-cn:/develop/add-fire/mm3
unity-tech-cn:/develop/add-fire/continuous
unity-tech-cn:/develop/add-fire/ghost
unity-tech-cn:/develop/add-fire/policy-tests
unity-tech-cn:/develop/add-fire/export-discrete
unity-tech-cn:/develop/add-fire/test-simple-rl-fix-resnet
unity-tech-cn:/develop/add-fire/remove-currdoc
unity-tech-cn:/develop/add-fire/clean2
unity-tech-cn:/develop/add-fire/doc-cleanups
unity-tech-cn:/develop/add-fire/changelog
unity-tech-cn:/develop/add-fire/mm2
unity-tech-cn:/develop/model-transfer/add-physics
unity-tech-cn:/develop/model-transfer/train
unity-tech-cn:/develop/jit/experiments
unity-tech-cn:/exp-vince/sep30-2020
unity-tech-cn:/hh-develop-gridsensor-tests/static
unity-tech-cn:/develop/hybrid-actions/distlist
unity-tech-cn:/develop/bullet-hell/buffer
unity-tech-cn:/goal-conditioning/new
unity-tech-cn:/goal-conditioning/sensors-2
unity-tech-cn:/goal-conditioning/sensors-3-pytest-fix
unity-tech-cn:/goal-conditioning/grid-world
unity-tech-cn:/soccer-comms/disc
unity-tech-cn:/develop/centralizedcritic/counterfact
unity-tech-cn:/develop/centralizedcritic/mm
unity-tech-cn:/develop/centralizedcritic/nonego
unity-tech-cn:/develop/zombieteammanager/disableagent
unity-tech-cn:/develop/zombieteammanager/killfirst
unity-tech-cn:/develop/superpush/int
unity-tech-cn:/develop/superpush/branch-cleanup
unity-tech-cn:/develop/teammanager/int
unity-tech-cn:/develop/teammanager/cubewar-nocycle
unity-tech-cn:/develop/teammanager/cubewars
unity-tech-cn:/develop/superpush/int/hunter
unity-tech-cn:/goal-conditioning/new/allo-crawler
unity-tech-cn:/develop/coma2/clip
unity-tech-cn:/develop/coma2/singlenetwork
unity-tech-cn:/develop/coma2/samenet
unity-tech-cn:/develop/coma2/fixgroup
unity-tech-cn:/develop/coma2/samenet/sum
unity-tech-cn:/hh-develop-dodgeball/goy-input
unity-tech-cn:/develop/soccer-groupman/mod
unity-tech-cn:/develop/soccer-groupman/mod/hunter
unity-tech-cn:/develop/soccer-groupman/mod/hunter/cine
unity-tech-cn:/ai-hw-2021/tensor-applier
此合并请求有变更与目标分支冲突。
/protobuf-definitions/proto/mlagents_envs/communicator_objects/agent_info.proto
/config/ppo/PushBlock.yaml
/Project/Packages/manifest.json
/Project/ProjectSettings/TagManager.asset
/Project/ProjectSettings/GraphicsSettings.asset
/Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs
/Project/Assets/ML-Agents/Examples/Crawler/Scripts/CrawlerAgent.cs
/Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayAgent.cs
/Project/Assets/ML-Agents/Examples/Hallway/Prefabs/SymbolFinderArea.prefab
/Project/Assets/ML-Agents/Examples/Soccer/Scenes/SoccerTwos.unity
/Project/Assets/ML-Agents/Examples/Soccer/Prefabs/SoccerFieldTwos.prefab
/com.unity.ml-agents/Runtime/Communicator/GrpcExtensions.cs
/com.unity.ml-agents/Runtime/Agent.cs
/com.unity.ml-agents/Runtime/Grpc/CommunicatorObjects/AgentInfo.cs
/com.unity.ml-agents/Runtime/Policies/BehaviorParameters.cs
/ml-agents-envs/mlagents_envs/rpc_utils.py
/ml-agents-envs/mlagents_envs/communicator_objects/agent_info_pb2.py
/ml-agents-envs/mlagents_envs/communicator_objects/agent_info_pb2.pyi
/ml-agents-envs/mlagents_envs/base_env.py
/ml-agents/mlagents/trainers/ghost/trainer.py
/ml-agents/mlagents/trainers/optimizer/torch_optimizer.py
/ml-agents/mlagents/trainers/agent_processor.py
/ml-agents/mlagents/trainers/behavior_id_utils.py
/ml-agents/mlagents/trainers/policy/torch_policy.py
/ml-agents/mlagents/trainers/ppo/optimizer_torch.py
/ml-agents/mlagents/trainers/ppo/trainer.py
/ml-agents/mlagents/trainers/tests/test_buffer.py
/ml-agents/mlagents/trainers/buffer.py
/ml-agents/mlagents/trainers/torch/layers.py
/ml-agents/mlagents/trainers/torch/attention.py
/ml-agents/mlagents/trainers/torch/components/bc/module.py
/ml-agents/mlagents/trainers/torch/utils.py
/ml-agents/mlagents/trainers/torch/networks.py
/ml-agents/mlagents/trainers/torch/encoders.py
/ml-agents/mlagents/trainers/trajectory.py
/Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/CollisionCallbacks.cs
/Project/Assets/ML-Agents/Examples/PushBlock/Scripts/GoalDetectTrigger.cs
/Project/Assets/ML-Agents/Examples/PushBlock/Scripts/SimpleNPC.cs
/Project/Assets/ML-Agents/Examples/PushBlock/Scripts/SimpleNPC.cs.meta
/Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/CollisionCallbacks.cs.meta
/Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockCollab.onnx
/Project/Assets/ML-Agents/Examples/PushBlock/Scenes/PushBlockCollab.unity
/Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushBlockEnvController.cs
/Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushAgentCollab.cs
/Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockCollab.onnx.meta
3 次代码提交
作者 | SHA1 | 备注 | 提交日期 |
---|---|---|---|
Ruo-Ping Dong | fb4a3bd2 | fix grouping for int id | 4 年前 |
Ruo-Ping Dong | 910da750 | change teammanager id from string to int | 4 年前 |
Ruo-Ping Dong | f48d3859 | baseline with teammanager as ID | 4 年前 |
共有 100 个文件被更改,包括 17184 次插入 和 175 次删除
-
2config/ppo/PushBlock.yaml
-
1com.unity.ml-agents/Runtime/Policies/BehaviorParameters.cs
-
40com.unity.ml-agents/Runtime/Agent.cs
-
1com.unity.ml-agents/Runtime/Communicator/GrpcExtensions.cs
-
39com.unity.ml-agents/Runtime/Grpc/CommunicatorObjects/AgentInfo.cs
-
1protobuf-definitions/proto/mlagents_envs/communicator_objects/agent_info.proto
-
3Project/ProjectSettings/TagManager.asset
-
1Project/ProjectSettings/GraphicsSettings.asset
-
2Project/ProjectSettings/UnityConnectSettings.asset
-
1Project/Packages/manifest.json
-
13Project/Assets/ML-Agents/Examples/Crawler/Scripts/CrawlerAgent.cs
-
8Project/Assets/ML-Agents/Examples/Soccer/Prefabs/SoccerFieldTwos.prefab
-
146Project/Assets/ML-Agents/Examples/Soccer/Scenes/SoccerTwos.unity
-
22Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpAgent.cs
-
2Project/Assets/ML-Agents/Examples/Hallway/Scenes/Hallway.unity.meta
-
932Project/Assets/ML-Agents/Examples/Hallway/Prefabs/SymbolFinderArea.prefab
-
22Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayAgent.cs
-
11ml-agents-envs/mlagents_envs/communicator_objects/agent_info_pb2.py
-
7ml-agents-envs/mlagents_envs/communicator_objects/agent_info_pb2.pyi
-
22ml-agents-envs/mlagents_envs/rpc_utils.py
-
14ml-agents-envs/mlagents_envs/base_env.py
-
5ml-agents/mlagents/trainers/policy/torch_policy.py
-
29ml-agents/mlagents/trainers/tests/test_buffer.py
-
71ml-agents/mlagents/trainers/buffer.py
-
30ml-agents/mlagents/trainers/optimizer/torch_optimizer.py
-
7ml-agents/mlagents/trainers/ppo/trainer.py
-
9ml-agents/mlagents/trainers/ppo/optimizer_torch.py
-
75ml-agents/mlagents/trainers/trajectory.py
-
14ml-agents/mlagents/trainers/ghost/trainer.py
-
12ml-agents/mlagents/trainers/torch/utils.py
-
2ml-agents/mlagents/trainers/torch/components/bc/module.py
-
25ml-agents/mlagents/trainers/torch/encoders.py
-
17ml-agents/mlagents/trainers/torch/layers.py
-
8ml-agents/mlagents/trainers/torch/attention.py
-
177ml-agents/mlagents/trainers/torch/networks.py
-
104ml-agents/mlagents/trainers/agent_processor.py
-
42ml-agents/mlagents/trainers/behavior_id_utils.py
-
63config/ppo/WallJumpCollab.yaml
-
26config/ppo/HallwayCollab.yaml
-
28config/ppo/PushBlockZombie.yaml
-
8com.unity.ml-agents.extensions/Runtime/Teams.meta
-
3com.unity.ml-agents/Runtime/ITeamManager.cs.meta
-
14com.unity.ml-agents/Runtime/ITeamManager.cs
-
13com.unity.ml-agents/Runtime/TeamManagerIdCounter.cs
-
11com.unity.ml-agents/Runtime/TeamManagerIdCounter.cs.meta
-
50Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallAreaScoring.cs
-
11Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallAreaScoring.cs.meta
-
11Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpCollabAgent.cs.meta
-
67Project/Assets/ML-Agents/Examples/WallJump/Scripts/WallJumpCollabAgent.cs
-
7Project/Assets/ML-Agents/Examples/WallJump/Scenes/WallJumpCollab.unity.meta
-
1001Project/Assets/ML-Agents/Examples/WallJump/Scenes/WallJumpCollab.unity
-
7Project/Assets/ML-Agents/Examples/WallJump/Prefabs/WallJumpCollabArea.prefab.meta
-
1001Project/Assets/ML-Agents/Examples/WallJump/Prefabs/WallJumpCollabArea.prefab
-
11Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/CollisionCallbacks.cs.meta
-
143Project/Assets/ML-Agents/Examples/SharedAssets/Scripts/CollisionCallbacks.cs
-
7Project/Assets/ML-Agents/Examples/Hallway/Scenes/HallwayCollab.unity.meta
-
1001Project/Assets/ML-Agents/Examples/Hallway/Scenes/HallwayCollab.unity
-
11Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayCollabAgent.cs.meta
-
11Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayTeamManager.cs.meta
-
204Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayCollabAgent.cs
-
24Project/Assets/ML-Agents/Examples/Hallway/Scripts/HallwayTeamManager.cs
-
566Project/Assets/ML-Agents/Examples/Hallway/TFModels/HallwayCollab.onnx
-
14Project/Assets/ML-Agents/Examples/Hallway/TFModels/HallwayCollab.onnx.meta
-
1001Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockCollab.onnx
-
14Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockCollab.onnx.meta
-
1001Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockCC.onnx
-
14Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockCC.onnx.meta
-
1001Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockMaster.onnx
-
14Project/Assets/ML-Agents/Examples/PushBlock/TFModels/PushBlockMaster.onnx.meta
-
7Project/Assets/ML-Agents/Examples/PushBlock/Prefabs/PushBlockCollabArea.prefab.meta
-
1001Project/Assets/ML-Agents/Examples/PushBlock/Prefabs/PushBlockCollabArea.prefab
-
7Project/Assets/ML-Agents/Examples/PushBlock/Prefabs/ZombiePushBlockCollabArea.prefab.meta
-
1001Project/Assets/ML-Agents/Examples/PushBlock/Prefabs/ZombiePushBlockCollabArea.prefab
-
1001Project/Assets/ML-Agents/Examples/PushBlock/Prefabs/ZombiePushBlockDeathCollabArea.prefab
-
7Project/Assets/ML-Agents/Examples/PushBlock/Prefabs/ZombiePushBlockDeathCollabArea.prefab.meta
-
9Project/Assets/ML-Agents/Examples/PushBlock/Scenes/PushBlockCollab.unity.meta
-
969Project/Assets/ML-Agents/Examples/PushBlock/Scenes/PushBlockCollab.unity
-
997Project/Assets/ML-Agents/Examples/PushBlock/Scenes/ZombiePushBlock.unity
-
9Project/Assets/ML-Agents/Examples/PushBlock/Scenes/ZombiePushBlock.unity.meta
-
1001Project/Assets/ML-Agents/Examples/PushBlock/Scenes/1ZombieVs2AgentsPushBlock.unity
-
9Project/Assets/ML-Agents/Examples/PushBlock/Scenes/2ZombieVs3AgentsPushBlock.unity.meta
-
9Project/Assets/ML-Agents/Examples/PushBlock/Scenes/1ZombieVs2AgentsPushBlock.unity.meta
-
860Project/Assets/ML-Agents/Examples/PushBlock/Scenes/2ZombieVs3AgentsPushBlock.unity
-
12Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushAgentCollab.cs.meta
-
11Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushBlockEnvController.cs.meta
-
60Project/Assets/ML-Agents/Examples/PushBlock/Scripts/GoalDetectTrigger.cs
-
11Project/Assets/ML-Agents/Examples/PushBlock/Scripts/GoalDetectTrigger.cs.meta
-
241Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushBlockEnvController.cs
-
116Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushAgentCollab.cs
-
289Project/Assets/ML-Agents/Examples/PushBlock/Scripts/ZombiePushBlockEnvController.cs
-
11Project/Assets/ML-Agents/Examples/PushBlock/Scripts/ZombiePushBlockEnvController.cs.meta
-
45Project/Assets/ML-Agents/Examples/PushBlock/Scripts/SimpleNPC.cs
-
11Project/Assets/ML-Agents/Examples/PushBlock/Scripts/SimpleNPC.cs.meta
-
11Project/Assets/ML-Agents/Examples/PushBlock/Scripts/ZombiePushBlockDeathEnvController.cs.meta
-
15Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushBlockTeamManager.cs
-
11Project/Assets/ML-Agents/Examples/PushBlock/Scripts/PushBlockTeamManager.cs.meta
-
316Project/Assets/ML-Agents/Examples/PushBlock/Scripts/ZombiePushBlockDeathEnvController.cs
-
26com.unity.ml-agents.extensions/Runtime/Teams/BaseTeamManager.cs
-
11com.unity.ml-agents.extensions/Runtime/Teams/BaseTeamManager.cs.meta
|
|||
fileFormatVersion: 2 |
|||
guid: d6d6a33ed0e18459a8d61817d600978a |
|||
guid: 71d1487c63f604ff6985cc2f23c7afbf |
|||
DefaultImporter: |
|||
externalObjects: {} |
|||
userData: |
932
Project/Assets/ML-Agents/Examples/Hallway/Prefabs/SymbolFinderArea.prefab
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
|
|||
behaviors: |
|||
SmallWallJump: |
|||
trainer_type: ppo |
|||
hyperparameters: |
|||
batch_size: 128 |
|||
buffer_size: 2048 |
|||
learning_rate: 0.0003 |
|||
beta: 0.005 |
|||
epsilon: 0.2 |
|||
lambd: 0.95 |
|||
num_epoch: 3 |
|||
learning_rate_schedule: linear |
|||
network_settings: |
|||
normalize: false |
|||
hidden_units: 256 |
|||
num_layers: 2 |
|||
vis_encode_type: simple |
|||
reward_signals: |
|||
extrinsic: |
|||
gamma: 0.99 |
|||
strength: 1.0 |
|||
keep_checkpoints: 5 |
|||
max_steps: 15000000 |
|||
time_horizon: 128 |
|||
summary_freq: 20000 |
|||
threaded: true |
|||
environment_parameters: |
|||
big_wall_height: |
|||
curriculum: |
|||
- name: Lesson0 |
|||
completion_criteria: |
|||
measure: progress |
|||
behavior: SmallWallJump |
|||
signal_smoothing: true |
|||
min_lesson_length: 100 |
|||
threshold: 0.1 |
|||
value: 3 |
|||
- name: Lesson1 |
|||
completion_criteria: |
|||
measure: progress |
|||
behavior: SmallWallJump |
|||
signal_smoothing: true |
|||
min_lesson_length: 100 |
|||
threshold: 0.3 |
|||
value: 5 |
|||
- name: Lesson2 |
|||
completion_criteria: |
|||
measure: progress |
|||
behavior: SmallWallJump |
|||
signal_smoothing: true |
|||
min_lesson_length: 100 |
|||
threshold: 0.5 |
|||
value: 8 |
|||
- name: Lesson3 |
|||
completion_criteria: |
|||
measure: progress |
|||
behavior: SmallWallJump |
|||
signal_smoothing: true |
|||
min_lesson_length: 100 |
|||
threshold: 0.7 |
|||
value: 9 |
|||
- name: Lesson4 |
|||
value: 9 |
|
|||
behaviors: |
|||
HallwayCollab: |
|||
trainer_type: ppo |
|||
hyperparameters: |
|||
batch_size: 128 |
|||
buffer_size: 1024 |
|||
learning_rate: 0.0003 |
|||
beta: 0.01 |
|||
epsilon: 0.2 |
|||
lambd: 0.95 |
|||
num_epoch: 3 |
|||
learning_rate_schedule: linear |
|||
network_settings: |
|||
normalize: false |
|||
hidden_units: 128 |
|||
num_layers: 2 |
|||
vis_encode_type: simple |
|||
reward_signals: |
|||
extrinsic: |
|||
gamma: 0.99 |
|||
strength: 1.0 |
|||
keep_checkpoints: 5 |
|||
max_steps: 10000000 |
|||
time_horizon: 64 |
|||
summary_freq: 10000 |
|||
threaded: true |
|
|||
behaviors: |
|||
PushBlock: |
|||
trainer_type: ppo |
|||
hyperparameters: |
|||
batch_size: 128 |
|||
buffer_size: 2048 |
|||
learning_rate: 0.0003 |
|||
beta: 0.01 |
|||
epsilon: 0.2 |
|||
lambd: 0.95 |
|||
num_epoch: 3 |
|||
learning_rate_schedule: linear |
|||
network_settings: |
|||
normalize: false |
|||
hidden_units: 256 |
|||
num_layers: 2 |
|||
vis_encode_type: simple |
|||
reward_signals: |
|||
extrinsic: |
|||
gamma: 0.99 |
|||
strength: 1.0 |
|||
keep_checkpoints: 5 |
|||
max_steps: 6000000 #2000000 |
|||
time_horizon: 64 |
|||
summary_freq: 60000 |
|||
threaded: true |
|||
env_settings: |
|||
num_envs: 3 |
|
|||
fileFormatVersion: 2 |
|||
guid: 77124df6c18c4f669052016b3116147e |
|||
folderAsset: yes |
|||
DefaultImporter: |
|||
externalObjects: {} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
|
|||
fileFormatVersion: 2 |
|||
guid: 75810d91665e4477977eb78c9b15aeb3 |
|||
timeCreated: 1610057818 |
|
|||
using System.Collections.Generic; |
|||
using Unity.MLAgents.Sensors; |
|||
|
|||
namespace Unity.MLAgents |
|||
{ |
|||
public interface ITeamManager |
|||
{ |
|||
int GetId(); |
|||
|
|||
void RegisterAgent(Agent agent); |
|||
// TODO not sure this is all the info we need, maybe pass a class/struct instead.
|
|||
void OnAgentDone(Agent agent, Agent.DoneReason doneReason, List<ISensor> sensors); |
|||
} |
|||
} |
|
|||
using System.Threading; |
|||
|
|||
namespace Unity.MLAgents |
|||
{ |
|||
internal static class TeamManagerIdCounter |
|||
{ |
|||
static int s_Counter; |
|||
public static int GetTeamManagerId() |
|||
{ |
|||
return Interlocked.Increment(ref s_Counter); ; |
|||
} |
|||
} |
|||
} |
|
|||
fileFormatVersion: 2 |
|||
guid: 06456db1475d84371b35bae4855db3c6 |
|||
MonoImporter: |
|||
externalObjects: {} |
|||
serializedVersion: 2 |
|||
defaultReferences: [] |
|||
executionOrder: 0 |
|||
icon: {instanceID: 0} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
|
|||
using System.Collections; |
|||
using System.Collections.Generic; |
|||
using UnityEngine; |
|||
|
|||
public class WallAreaScoring : MonoBehaviour |
|||
{ |
|||
public GameObject[] agents; |
|||
WallJumpSettings m_WallJumpSettings; |
|||
Renderer m_GroundRenderer; |
|||
Material m_GroundMaterial; |
|||
|
|||
protected IEnumerator GoalScoredSwapGroundMaterial(Material mat, float time) |
|||
{ |
|||
m_GroundRenderer.material = mat; |
|||
yield return new WaitForSeconds(time); //wait for 2 sec
|
|||
m_GroundRenderer.material = m_GroundMaterial; |
|||
} |
|||
|
|||
public void Start() |
|||
{ |
|||
m_WallJumpSettings = FindObjectOfType<WallJumpSettings>(); |
|||
m_GroundRenderer = GetComponent<Renderer>(); |
|||
m_GroundMaterial = m_GroundRenderer.material; |
|||
} |
|||
|
|||
public void WinCondition() |
|||
{ |
|||
foreach (var agent in agents) |
|||
{ |
|||
WallJumpCollabAgent agentScript = agent.GetComponent<WallJumpCollabAgent>(); |
|||
agentScript.SetReward(1f); |
|||
agentScript.EndEpisode(); |
|||
} |
|||
StartCoroutine( |
|||
GoalScoredSwapGroundMaterial(m_WallJumpSettings.goalScoredMaterial, 1f)); |
|||
} |
|||
|
|||
public void LoseCondition() |
|||
{ |
|||
foreach (var agent in agents) |
|||
{ |
|||
WallJumpCollabAgent agentScript = agent.GetComponent<WallJumpCollabAgent>(); |
|||
agentScript.SetReward(-1f); |
|||
agentScript.EndEpisode(); |
|||
|
|||
} |
|||
StartCoroutine( |
|||
GoalScoredSwapGroundMaterial(m_WallJumpSettings.failMaterial, .2f)); |
|||
} |
|||
} |
|
|||
fileFormatVersion: 2 |
|||
guid: ad7213222795741f5b6ca2b332f16da9 |
|||
MonoImporter: |
|||
externalObjects: {} |
|||
serializedVersion: 2 |
|||
defaultReferences: [] |
|||
executionOrder: 0 |
|||
icon: {instanceID: 0} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
|
|||
fileFormatVersion: 2 |
|||
guid: 2cdbc0d9a64fe4b12a3ed4b81a151117 |
|||
MonoImporter: |
|||
externalObjects: {} |
|||
serializedVersion: 2 |
|||
defaultReferences: [] |
|||
executionOrder: 0 |
|||
icon: {instanceID: 0} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
|
|||
//Put this script on your blue cube.
|
|||
|
|||
using System.Collections; |
|||
using UnityEngine; |
|||
using Unity.MLAgents; |
|||
using Unity.Barracuda; |
|||
using Unity.MLAgents.Actuators; |
|||
using Unity.MLAgents.Sensors; |
|||
using Unity.MLAgentsExamples; |
|||
|
|||
public class WallJumpCollabAgent : WallJumpAgent |
|||
{ |
|||
Vector3 m_InitialPosition; |
|||
|
|||
WallAreaScoring m_Scoring; |
|||
public override void Initialize() |
|||
{ |
|||
m_WallJumpSettings = FindObjectOfType<WallJumpSettings>(); |
|||
m_Scoring = ground.GetComponent<WallAreaScoring>(); |
|||
m_Configuration = 5; |
|||
|
|||
m_AgentRb = GetComponent<Rigidbody>(); |
|||
// m_ShortBlockRb = shortBlock.GetComponent<Rigidbody>();
|
|||
m_SpawnAreaBounds = spawnArea.GetComponent<Collider>().bounds; |
|||
m_GroundRenderer = ground.GetComponent<Renderer>(); |
|||
m_GroundMaterial = m_GroundRenderer.material; |
|||
m_InitialPosition = transform.localPosition; |
|||
spawnArea.SetActive(false); |
|||
|
|||
m_ResetParams = Academy.Instance.EnvironmentParameters; |
|||
} |
|||
public override void OnEpisodeBegin() |
|||
{ |
|||
transform.localPosition = m_InitialPosition; |
|||
m_Configuration = 5; |
|||
m_AgentRb.velocity = default(Vector3); |
|||
} |
|||
|
|||
public override void OnActionReceived(ActionBuffers actionBuffers) |
|||
{ |
|||
MoveAgent(actionBuffers.DiscreteActions); |
|||
if (!Physics.Raycast(m_AgentRb.position, Vector3.down, 20)) |
|||
{ |
|||
m_Scoring.LoseCondition(); |
|||
} |
|||
} |
|||
|
|||
protected override void ConfigureAgent(int config) |
|||
{ |
|||
var localScale = wall.transform.localScale; |
|||
var height = m_ResetParams.GetWithDefault("big_wall_height", 9); |
|||
localScale = new Vector3( |
|||
localScale.x, |
|||
height, |
|||
localScale.z); |
|||
wall.transform.localScale = localScale; |
|||
} |
|||
|
|||
// Detect when the agent hits the goal
|
|||
protected override void OnTriggerStay(Collider col) |
|||
{ |
|||
if (col.gameObject.CompareTag("goal") && DoGroundCheck(true)) |
|||
{ |
|||
m_Scoring.WinCondition(); |
|||
} |
|||
} |
|||
} |
|
|||
fileFormatVersion: 2 |
|||
guid: 136090e065a8f48bfb97ea3083893d8a |
|||
DefaultImporter: |
|||
externalObjects: {} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
1001
Project/Assets/ML-Agents/Examples/WallJump/Scenes/WallJumpCollab.unity
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
|
|||
fileFormatVersion: 2 |
|||
guid: ff1a5743be49d43f08378dcd76451821 |
|||
PrefabImporter: |
|||
externalObjects: {} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
1001
Project/Assets/ML-Agents/Examples/WallJump/Prefabs/WallJumpCollabArea.prefab
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
|
|||
fileFormatVersion: 2 |
|||
guid: 506de7b261f374159a5cdfdb0ff48c0c |
|||
MonoImporter: |
|||
externalObjects: {} |
|||
serializedVersion: 2 |
|||
defaultReferences: [] |
|||
executionOrder: 0 |
|||
icon: {instanceID: 0} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
|
|||
using UnityEngine; |
|||
using Random = UnityEngine.Random; |
|||
using Unity.MLAgents; |
|||
using UnityEngine.Events; |
|||
|
|||
namespace Unity.MLAgentsExamples |
|||
{ |
|||
/// <summary>
|
|||
/// Utility class to allow target placement and collision detection with an agent
|
|||
/// Add this script to the target you want the agent to touch.
|
|||
/// Callbacks will be triggered any time the target is touched with a collider tagged as 'tagToDetect'
|
|||
/// </summary>
|
|||
public class CollisionCallbacks : MonoBehaviour |
|||
{ |
|||
// [System.Serializable] public class BoolEvent : UnityEvent<bool> { }
|
|||
// [SerializeField] BoolEvent boolEvent = new BoolEvent();
|
|||
// public void OnBoolEvent(bool value)
|
|||
// {
|
|||
// Debug.Log($"OnBoolEvent {value}");
|
|||
// }
|
|||
|
|||
|
|||
[Header("Collider Tag To Detect")] |
|||
public string tagToDetect = "agent"; //collider tag to detect
|
|||
|
|||
// [Header("Target Placement")]
|
|||
// public float spawnRadius; //The radius in which a target can be randomly spawned.
|
|||
// public bool respawnIfTouched; //Should the target respawn to a different position when touched
|
|||
//
|
|||
// [Header("Target Fell Protection")]
|
|||
// public bool respawnIfFallsOffPlatform = true; //If the target falls off the platform, reset the position.
|
|||
// public float fallDistance = 5; //distance below the starting height that will trigger a respawn
|
|||
//
|
|||
//
|
|||
// private Vector3 m_startingPos; //the starting position of the target
|
|||
// private Agent m_agentTouching; //the agent currently touching the target
|
|||
|
|||
[System.Serializable] |
|||
// public class TriggerEvent : UnityEvent<string>
|
|||
public class TriggerEvent : UnityEvent<Collider> |
|||
{ |
|||
} |
|||
|
|||
[Header("Trigger Callbacks")] |
|||
public TriggerEvent onTriggerEnterEvent = new TriggerEvent(); |
|||
public TriggerEvent onTriggerStayEvent = new TriggerEvent(); |
|||
public TriggerEvent onTriggerExitEvent = new TriggerEvent(); |
|||
|
|||
[System.Serializable] |
|||
public class CollisionEvent : UnityEvent<Collision, Transform> |
|||
{ |
|||
} |
|||
|
|||
[Header("Collision Callbacks")] |
|||
public CollisionEvent onCollisionEnterEvent = new CollisionEvent(); |
|||
public CollisionEvent onCollisionStayEvent = new CollisionEvent(); |
|||
public CollisionEvent onCollisionExitEvent = new CollisionEvent(); |
|||
|
|||
// // Start is called before the first frame update
|
|||
// void OnEnable()
|
|||
// {
|
|||
// m_startingPos = transform.position;
|
|||
// if (respawnIfTouched)
|
|||
// {
|
|||
// MoveTargetToRandomPosition();
|
|||
// }
|
|||
// }
|
|||
|
|||
// void Update()
|
|||
// {
|
|||
// if (respawnIfFallsOffPlatform)
|
|||
// {
|
|||
// if (transform.position.y < m_startingPos.y - fallDistance)
|
|||
// {
|
|||
// Debug.Log($"{transform.name} Fell Off Platform");
|
|||
// MoveTargetToRandomPosition();
|
|||
// }
|
|||
// }
|
|||
// }
|
|||
|
|||
// /// <summary>
|
|||
// /// Moves target to a random position within specified radius.
|
|||
// /// </summary>
|
|||
// public void MoveTargetToRandomPosition()
|
|||
// {
|
|||
// var newTargetPos = m_startingPos + (Random.insideUnitSphere * spawnRadius);
|
|||
// newTargetPos.y = m_startingPos.y;
|
|||
// transform.position = newTargetPos;
|
|||
// }
|
|||
|
|||
private void OnCollisionEnter(Collision col) |
|||
{ |
|||
if (col.transform.CompareTag(tagToDetect)) |
|||
{ |
|||
onCollisionEnterEvent.Invoke(col, transform); |
|||
// if (respawnIfTouched)
|
|||
// {
|
|||
// MoveTargetToRandomPosition();
|
|||
// }
|
|||
} |
|||
} |
|||
|
|||
private void OnCollisionStay(Collision col) |
|||
{ |
|||
if (col.transform.CompareTag(tagToDetect)) |
|||
{ |
|||
onCollisionStayEvent.Invoke(col, transform); |
|||
} |
|||
} |
|||
|
|||
private void OnCollisionExit(Collision col) |
|||
{ |
|||
if (col.transform.CompareTag(tagToDetect)) |
|||
{ |
|||
onCollisionExitEvent.Invoke(col, transform); |
|||
} |
|||
} |
|||
|
|||
private void OnTriggerEnter(Collider col) |
|||
{ |
|||
if (col.CompareTag(tagToDetect)) |
|||
{ |
|||
onTriggerEnterEvent.Invoke(col); |
|||
} |
|||
} |
|||
|
|||
private void OnTriggerStay(Collider col) |
|||
{ |
|||
if (col.CompareTag(tagToDetect)) |
|||
{ |
|||
onTriggerStayEvent.Invoke(col); |
|||
} |
|||
} |
|||
|
|||
private void OnTriggerExit(Collider col) |
|||
{ |
|||
if (col.CompareTag(tagToDetect)) |
|||
{ |
|||
onTriggerExitEvent.Invoke(col); |
|||
} |
|||
} |
|||
} |
|||
} |
|
|||
fileFormatVersion: 2 |
|||
guid: d6d6a33ed0e18459a8d61817d600978a |
|||
DefaultImporter: |
|||
externalObjects: {} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
1001
Project/Assets/ML-Agents/Examples/Hallway/Scenes/HallwayCollab.unity
文件差异内容过多而无法显示
查看文件
文件差异内容过多而无法显示
查看文件
|
|||
fileFormatVersion: 2 |
|||
guid: f7451777d89fd47418f0e1c3e2511919 |
|||
MonoImporter: |
|||
externalObjects: {} |
|||
serializedVersion: 2 |
|||
defaultReferences: [] |
|||
executionOrder: 0 |
|||
icon: {instanceID: 0} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
|
|||
fileFormatVersion: 2 |
|||
guid: 8b67166b7adef46febf8b570f92c400d |
|||
MonoImporter: |
|||
externalObjects: {} |
|||
serializedVersion: 2 |
|||
defaultReferences: [] |
|||
executionOrder: 0 |
|||
icon: {instanceID: 0} |
|||
userData: |
|||
assetBundleName: |
|||
assetBundleVariant: |
|
|||
using UnityEngine; |
|||
using Unity.MLAgents.Extensions.Teams; |
|||
using Unity.MLAgents.Actuators; |
|||
using Unity.MLAgents.Sensors; |
|||
|
|||
public class HallwayCollabAgent : HallwayAgent |
|||
{ |
|||
public GameObject symbolSGoal; |
|||
public GameObject symbolS; |
|||
public HallwayCollabAgent teammate; |
|||
public bool isSpotter = true; |
|||
int m_Message = 0; |
|||
|
|||
|
|||
[HideInInspector] |
|||
public int selection = 0; |
|||
|
|||
public override void Initialize() |
|||
{ |
|||
base.Initialize(); |
|||
if (isSpotter) |
|||
{ |
|||
var teamManager = new HallwayTeamManager(); |
|||
SetTeamManager(teamManager); |
|||
teammate.SetTeamManager(teamManager); |
|||
} |
|||
} |
|||
public override void OnEpisodeBegin() |
|||
{ |
|||
m_Message = -1; |
|||
|
|||
var agentOffset = 10f; |
|||
if (isSpotter) |
|||
{ |
|||
agentOffset = -15; |
|||
} |
|||
|
|||
if (!isSpotter) |
|||
{ |
|||
transform.position = new Vector3(0f + Random.Range(-3f, 3f), |
|||
1f, agentOffset + Random.Range(-5f, 5f)) |
|||
+ ground.transform.position; |
|||
transform.rotation = Quaternion.Euler(0f, Random.Range(0f, 360f), 0f); |
|||
} |
|||
else |
|||
{ |
|||
transform.position = new Vector3(0f, |
|||
1f, agentOffset) |
|||
+ ground.transform.position; |
|||
transform.rotation = Quaternion.Euler(0f, 0f, 0f); |
|||
} |
|||
|
|||
// Remove the randomness
|
|||
|
|||
m_AgentRb.velocity *= 0f; |
|||
if (isSpotter) |
|||
{ |
|||
var blockOffset = -9f; |
|||
// Only the Spotter has the correct selection
|
|||
selection = Random.Range(0, 3); |
|||
if (selection == 0) |
|||
{ |
|||
symbolO.transform.position = |
|||
new Vector3(0f, 2f, blockOffset) |
|||
+ ground.transform.position; |
|||
symbolX.transform.position = |
|||
new Vector3(0f, -1000f, blockOffset + Random.Range(-5f, 5f)) |
|||
+ ground.transform.position; |
|||
symbolS.transform.position = |
|||
new Vector3(0f, -1000f, blockOffset + Random.Range(-5f, 5f)) |
|||
+ ground.transform.position; |
|||
} |
|||
else if (selection == 1) |
|||
{ |
|||
symbolO.transform.position = |
|||
new Vector3(0f, -1000f, blockOffset + Random.Range(-5f, 5f)) |
|||
+ ground.transform.position; |
|||
symbolX.transform.position = |
|||
new Vector3(0f, 2f, blockOffset) |
|||
+ ground.transform.position; |
|||
symbolS.transform.position = |
|||
new Vector3(0f, -1000f, blockOffset + Random.Range(-5f, 5f)) |
|||
+ ground.transform.position; |
|||
} |
|||
else |
|||
{ |
|||
symbolO.transform.position = |
|||
new Vector3(0f, -1000f, blockOffset + Random.Range(-5f, 5f)) |
|||
+ ground.transform.position; |
|||
symbolX.transform.position = |
|||
new Vector3(0f, -1000f, blockOffset) |
|||
+ ground.transform.position; |
|||
symbolS.transform.position = |
|||
new Vector3(0f, 2f, blockOffset) |
|||
+ ground.transform.position; |
|||
} |
|||
|
|||
var goalPos = Random.Range(0, 7); |
|||
if (goalPos == 0) |
|||
{ |
|||
symbolOGoal.transform.position = new Vector3(7f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolXGoal.transform.position = new Vector3(0f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolSGoal.transform.position = new Vector3(-7f, 0.5f, 22.29f) + area.transform.position; |
|||
} |
|||
else if (goalPos == 1) |
|||
{ |
|||
symbolOGoal.transform.position = new Vector3(7f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolXGoal.transform.position = new Vector3(-7f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolSGoal.transform.position = new Vector3(0f, 0.5f, 22.29f) + area.transform.position; |
|||
} |
|||
else if (goalPos == 2) |
|||
{ |
|||
symbolOGoal.transform.position = new Vector3(-7f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolXGoal.transform.position = new Vector3(7f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolSGoal.transform.position = new Vector3(0f, 0.5f, 22.29f) + area.transform.position; |
|||
} |
|||
else if (goalPos == 3) |
|||
{ |
|||
symbolOGoal.transform.position = new Vector3(-7f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolXGoal.transform.position = new Vector3(0f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolSGoal.transform.position = new Vector3(7f, 0.5f, 22.29f) + area.transform.position; |
|||
} |
|||
else if (goalPos == 4) |
|||
{ |
|||
symbolOGoal.transform.position = new Vector3(0f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolXGoal.transform.position = new Vector3(-7f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolSGoal.transform.position = new Vector3(7f, 0.5f, 22.29f) + area.transform.position; |
|||
} |
|||
else |
|||
{ |
|||
symbolOGoal.transform.position = new Vector3(0f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolXGoal.transform.position = new Vector3(7f, 0.5f, 22.29f) + area.transform.position; |
|||
symbolSGoal.transform.position = new Vector3(-7f, 0.5f, 22.29f) + area.transform.position; |
|||
} |
|||
} |
|||
} |
|||
public override void CollectObservations(VectorSensor sensor) |
|||
{ |
|||
if (useVectorObs) |
|||
{ |
|||
sensor.AddObservation(StepCount / (float)MaxStep); |
|||
} |
|||
sensor.AddObservation(toOnehot(m_Message)); |
|||
} |
|||
|
|||
float[] toOnehot(int message) |
|||
{ |
|||
float[] onehot = new float[3]; |
|||
if (message < 0 || message >= 3) |
|||
{ |
|||
return onehot; |
|||
} |
|||
onehot[message] = 1f; |
|||
return onehot; |
|||
} |
|||
|
|||
public void tellAgent(int message) |
|||
{ |
|||
m_Message = message; |
|||
} |
|||
|
|||
public override void OnActionReceived(ActionBuffers actionBuffers) |
|||
{ |
|||
AddReward(-1f / MaxStep); |
|||
if (!isSpotter) |
|||
{ |
|||
MoveAgent(actionBuffers.DiscreteActions); |
|||
} |
|||
|
|||
int comm_act = actionBuffers.DiscreteActions[1]; |
|||
teammate.tellAgent(comm_act); |
|||
// if (isSpotter) // Test
|
|||
// {
|
|||
// teammate.tellAgent(selection);
|
|||
// }
|
|||
} |
|||
|
|||
void OnCollisionEnter(Collision col) |
|||
{ |
|||
if (col.gameObject.CompareTag("symbol_O_Goal") || col.gameObject.CompareTag("symbol_X_Goal") || col.gameObject.CompareTag("symbol_S_Goal")) |
|||
{ |
|||
if (!isSpotter) |
|||
{ |
|||
// Check the ground truth
|
|||
if ((teammate.selection == 0 && col.gameObject.CompareTag("symbol_O_Goal")) || |
|||
(teammate.selection == 1 && col.gameObject.CompareTag("symbol_X_Goal")) || |
|||
(teammate.selection == 2 && col.gameObject.CompareTag("symbol_S_Goal"))) |
|||
{ |
|||
SetReward(1f); |
|||
teammate.SetReward(1f); |
|||
StartCoroutine(GoalScoredSwapGroundMaterial(m_HallwaySettings.goalScoredMaterial, 0.5f)); |
|||
} |
|||
else |
|||
{ |
|||
SetReward(-0.1f); |
|||
teammate.SetReward(-0.1f); |
|||
StartCoroutine(GoalScoredSwapGroundMaterial(m_HallwaySettings.failMaterial, 0.5f)); |
|||
} |
|||
EndEpisode(); |
|||
teammate.EndEpisode(); |
|||
} |
|||
} |
|||
} |
|||
} |
|
|||
using System.Collections.Generic; |
|||
using Unity.MLAgents; |
|||
using Unity.MLAgents.Extensions.Teams; |
|||
using Unity.MLAgents.Sensors; |
|||
|
|||
public class HallwayTeamManager : BaseTeamManager |
|||
{ |
|||
List<Agent> m_AgentList = new List<Agent> { }; |
|||
|
|||
public override void RegisterAgent(Agent agent) |
|||
{ |
|||
m_AgentList.Add(agent); |
|||
} |
|||
|
|||
// public override void OnAgentDone(Agent agent, Agent.DoneReason doneReason, List<ISensor> sensors)
|
|||
// {
|
|||
|
|||
// }
|
|||
|
|||
// public override void AddTeamReward(float reward)
|
|||
// {
|
|||
|
|||
// }
|
|||
} |
|
|||
pytorch1.7:�� |
|||
Q |
|||
vector_observation22Slice_0"Slice* |
|||
axes@�* |
|||
ends@i�* |
|||
starts@ � |
|||
Q |
|||
vector_observation23Slice_1"Slice* |
|||
axes@�* |
|||
ends@o�* |
|||
starts@i� |
|||
4 |
|||
22 |
|||
2324Concat_2"Concat* |
|||
axis���������� |
|||
� |
|||
24 |
|||
/network_body.linear_encoder.seq_layers.0.weight |
|||
-network_body.linear_encoder.seq_layers.0.bias25Gemm_3"Gemm* |
|||
alpha �?�* |
|||
beta �?�* |
|||
transB� |
|||
|
|||
2526 Sigmoid_4"Sigmoid |
|||
|
|||
25 |
|||
2627Mul_5"Mul |
|||
� |
|||
27 |
|||
/network_body.linear_encoder.seq_layers.2.weight |
|||
-network_body.linear_encoder.seq_layers.2.bias28Gemm_6"Gemm* |
|||
alpha �?�* |
|||
beta �?�* |
|||
transB� |
|||
|
|||
2829 Sigmoid_7"Sigmoid |
|||
|
|||
28 |
|||
2930Mul_8"Mul |
|||
K |
|||
action_masks31Slice_9"Slice* |
|||
axes@�* |
|||
ends@�* |
|||
starts@ � |
|||
L |
|||
action_masks32Slice_10"Slice* |
|||
axes@�* |
|||
ends@�* |
|||
starts@� |
|||
� |
|||
30 |
|||
5action_model._discrete_distribution.branches.0.weight |
|||
3action_model._discrete_distribution.branches.0.bias33Gemm_11"Gemm* |
|||
alpha �?�* |
|||
beta �?�* |
|||
transB� |
|||
134Constant_12"Constant* |
|||
value*J ��� |
|||
|
|||
31 |
|||
3435Mul_13"Mul |
|||
136Constant_14"Constant* |
|||
value*J �?� |
|||
|
|||
35 |
|||
3637Add_15"Add |
|||
|
|||
33 |
|||
3138Mul_16"Mul |
|||
139Constant_17"Constant* |
|||
value*J ��L� |
|||
|
|||
37 |
|||
3940Mul_18"Mul |
|||
|
|||
38 |
|||
4041Sub_19"Sub |
|||
* |
|||
4142 |
|||
Softmax_20"Softmax* |
|||
axis� |
|||
� |
|||
30 |
|||
5action_model._discrete_distribution.branches.1.weight |
|||
3action_model._discrete_distribution.branches.1.bias43Gemm_21"Gemm* |
|||
alpha �?�* |
|||
beta �?�* |
|||
transB� |
|||
144Constant_22"Constant* |
|||
value*J ��� |
|||
|
|||
32 |
|||
4445Mul_23"Mul |
|||
146Constant_24"Constant* |
|||
value*J �?� |
|||
|
|||
45 |
|||
4647Add_25"Add |
|||
|
|||
43 |
|||
3248Mul_26"Mul |
|||
149Constant_27"Constant* |
|||
value*J ��L� |
|||
|
|||
47 |
|||
4950Mul_28"Mul |
|||
|
|||
48 |
|||
5051Sub_29"Sub |
|||
* |
|||
5152 |
|||
Softmax_30"Softmax* |
|||
axis� |
|||
153Constant_31"Constant* |
|||
value*J���3� |
|||
|
|||
42 |
|||
5354Add_32"Add |
|||
|
|||
5455Log_33"Log |
|||
156Constant_34"Constant* |
|||
value*J���3� |
|||
|
|||
52 |
|||
5657Add_35"Add |
|||
|
|||
5758Log_36"Log |
|||
: |
|||
55 |
|||
58discrete_actions Concat_37"Concat* |
|||
axis� |
|||
0 |
|||
55 |
|||
58action Concat_38"Concat* |
|||
axis� |
|||
<memory_sizeConstant_39"Constant* |
|||
value* |
|||
J �torch-jit-export*OB3action_model._discrete_distribution.branches.0.biasJ���
��;ۺ���#�;�U<*��B5action_model._discrete_distribution.branches.0.weightJ�`�����=�}{<�'0���_];�{�:��*����� 鼦G <>�ջ�����ܗ��P��C�_<Yj����ֺǟ����;��w���ʼr�O��y�<���e��;��케X�<Bhļ8d�;�+<����滯����d���V�ê�<Vp��s����;�^6�"X�|��G;D<��4�����kB�;�5k���$=���� |
|||
e<�V��<�D;<�[^;d=*��r����m<13�]m}5[�v���������֝<��ϼ�Jռ��<�]�����<����C)�eж��R�n��3G<̲X�Lz$uǻ���<�5n��;λ5�;����q��T��������94&�����t!�<Y��==F���;B>���6���x��{�:��뺁S���%�뼛�=�,�<�༘�ۼ&��$����v�;@�:��D<:c��ŗ��?Ĝ<� ���� �::AԼW_*���6�>��o��:V���� �����<�%�hD����=<+-�=�ۄ��G=ͣ<|=��=��= �����v�<� �=���==Ͻ�Wy�݆ʼ���=UbI=���=`)�<�Ѡ��5���{�<�҉=��J=��(�I�E=�of���=OK=��q;��p���g�t��=��?=�8o��K�<[k�;fs
�RT��]�c<s���R��]����=����>=����y1 ���м�`D=�� |
|||
=vU��A(=AQ�=ԚJ=
���!���>h�ἐlۼEॽ�a)=ڒ�����<wؘ=����f�p0�<��5=� h��Ț�K��������
=|�<�!�=� |
|||
&�~6�=mO����j<|Tg�#f|=��(�4�=�.�#<�7[ >���D�<#낽:�����˼ӭ<qq��}�����=����+Դ�6:��i7�f$5=(P;�S<�K�{�=�w���h�W]���� =_jg�%y=�V=L+<���<�Ӏ=�������<z=迼=+�=�<�k�����=�R��d˃�MRu�� y�T��<����k�;<罻���<^ͼg2<�q���:t�;����&�<{��<C2?�����m��^�Sc��*���H��������<2�U���k��R�'\3<Q�H=B;��伓�H��b<U� �P���`��,�<�) |
|||
�if��o"�<��Ҽr3�:��ֻ��f<���:���=<?�=�R���9�;p*�<]Y.���������4d�3r�G������۬���`��\�0<����>=#��;= �|<��K�X�Ir4�sd¼�*<��'c=�)�<G<7��<�>���o=�,���=jo'�po�<#��^v< ��;;��<� |
|||
6��`e�l�<oJ�?��<%��<c���pIo=g���>���m�<���;������<�/�eG+�D�J=d |
|||
<�.{<�z¼�ؼ���`�<~��<$'����^� ���;�5�������̼���<rT`�D�|;r\<R2��@A$���>��0ͻځ���1�,��;�B=�F <�� |
|||
�;��=�#���굼��;ת =z|`=�=��»�U����F=�ʊ��m�=�$�<C�H�2�p���M=��qC��}���i��Bک<֣?�DH<�S���r6���o�H��=v�^����(m�B |
|||
�=�Pټꧽ�^�{��=���1�[=O��=�+�=�O�=��e<'(6�2��;����m�<j��=H��<Yf�=���=�i^=J=�ω� ��9:��l�<�d�=�-�=Jwr��K����=Xy����}=����A�=(�p=�"��J꒽���<����HЍ��҄=r�>��=���=���=M�=�M ���=(���8s=�;��=E�����=)���2Ľ�]e=T� |
|||
��|=G��=}���C�<�<�=�懽�\>�%=X ��gAN=�}��]��Ǡa=�?<��S<��<)'f<}�x<r�'=s
==�ɺ�@l��0X�#���ׄ4��W���á=ө�����=��n<r�N=�S0����_=����r,�$w�=߹�;
�_��j��ܛ��7�^=[�-<d���A{ǽI8��[�P�][�=V=�<�Ґ�)�A��~���/�V@>=�ʪ=<�,3o=��:����,�=Be�=��-V��>H=��)=���H�#z�;�U<ӌ=c���QҦ=��*�p�h=`i*�Q�=�փ<?+���ݎ��Ô<%�<t�4=*Uq=`,�=ߢ������nR��t�<96�<{���U@�:i0"=��=���=�`�*ڽ����i�q=�Ƽ��Q�;o�=�!��C6=����A������`X�=� H=��=2D�=6:���u�d���YF̼�,��)VŽ�!ǽHI1�`Nz�z�I��~:=f��z��n�"�e>:���=v���ܑ� |
|||
��|%�=8�=[ap���x=��|���
=TZ���̠�ͱ�=��=��8�J|��?�]�<))k="T��0o��/���q�=$=N�=��C=�E�=�f=���T=Uj>��
���ཐ&��� μsb����==rk��J��*CB3action_model._discrete_distribution.branches.1.biasJЕ?�Е?<*��B5action_model._discrete_distribution.branches.1.weightJ����f�<�m����;øP<��<��;�x����;�#����<��<1���軝 |
|||
���Ԗ<�4<�� ��(����;�V��"}{<j�~��ze���A=s���,<C ��G"=��?�mu<Q~�<NU�<a���\��(?<���;��Q?;��ڼ��/<Y7N;��~��|�����<bE�;4E��$D���D��ɰ<�6��j�����;�������!�;o*<=��������3k�<䍖;ӑ ;��v<{����~<������#;F�������":��+5;�/&��<�<W�x<�^Y<Y��FOm<�J�<���~�=�ą��nѻWoϹ6xl:%�<��<�꼻=��<+��<�Z����_<1����0&L�G��_��(�l��Q�<<1'���!��+�����<�oǼ\�;ל�;�!�f_�����;Vx<��;�L�:9)�<%Z�;�&��Ѡ<D�r;D[漨�F<���#~�<�r�;��$<?���Mژ�-*���.�;[�?��;���<���5)�T`Ѽ]�<Jd<
��;e�ü������W<m��;&2+�K����,�8� �`ѱ�X�;�\Ӱ�;[�;�J�<�<���*�9s7��������L�s��A�ټ/AѼ���<���;���˷�L��P�;�ܫ<��Z�<O��:$<�.W;����z�<����e�A�;��� R��c6z<��X<�����";
�!<)/�0>1<������x<��<�/���j�:�+����;�懼�z/=_<Z�<p+Լ��]<������$>�:����a��+�<�B�;,���Q�W�@<f��0��;�X��҄���w�ɯ�� �<����kn��^X��{��E�<�==�^�<@x�<v��9 r�� ��P����U<�5�<Rސ<G���=�ja;b ���.<�O�<�;������U�;���86
=�k��i���y�<[?���;8J��]j����`�<���<U�<*Baction_output_shapeJ �@*(Bdiscrete_action_output_shapeJ �@*!Bis_continuous_controlJ *��B-network_body.linear_encoder.seq_layers.0.biasJ�B�#=ŌE=��<�$c=�U =g�1<��V=C�=��9=h�=Űn��N<C� =�r=B.K=g袺~G)=t<�!�;_z%;T <�Y��G=���<��*�cf;���<�S:<�["=�Z�<�N�<��$=`��<ɷ�<;�<�#t<���;�k��%#=!A=��H<^b�<l�ݻ �=�a%<�R�<��<�����3=(�<R@�Y�*<ɨ1<tDH;e[�< �<>�<�'�<��=�'�;�hM<��&=��Z<I��<ٳ� �=��;�#=�&�<��< |