235 次代码提交 (5ef902bf-7571-490d-ae8d-bcffd402453f)

作者 SHA1 备注 提交日期
GitHub 8317a659 Behavioral Cloning & Trainers Reorg (#328) 7 年前
GitHub e11dae1d Python Testing & Image Inference Improvements (#353) 7 年前
eshvk 23981dbf [containerization] CPU based containerization to support all environments that don't use observations 7 年前
Arthur Juliani b8a4f5f1 Add Hallway envronment to validate LSTM models 7 年前
eshvk 030ac5c5 [cleanup] Add a new type hint to call a dictionary of BrainInfo objects as an AllBrainInfo. Propagate this hint to all methods. Some pep8 cleanups. 7 年前
Arthur Juliani c3644f56 Buffer fix for properly masking gradients 7 年前
GitHub f8d27dc5 Merge branch 'development-0.3' into feature/LSTM2 7 年前
GitHub f134016b On Demand Decision (#308) 7 年前
GitHub cfc6bdc8 [Fix] The environment logs information about itself when lauched. (#395) 7 年前
eshvk 2d2eb64b [containers] Enables container support for scenes that use visual observations 7 年前
GitHub 237b41f9 Hotfix 0.3.0c (#618) 7 年前
GitHub 38098a12 [Fixed BC with LSTM] (#766) 7 年前
GitHub 7914387f Develop communicator redesign (#638) 7 年前
GitHub c17937ef Curiosity Driven Exploration & Pyramids Environments (#739) 7 年前
Arthur Juliani d7338050 Enable concurrent sessions 7 年前
Arthur Juliani 5d402be9 Minor Optimizations (#836) 7 年前
vincentg 3c4cb523 some hack to make windows save the model when do ctrl+c 7 年前
Arthur Juliani 195ac934 Merge branch 'develop' into develop-runs 7 年前
vincentpierre e47cec56 [Initial Commit] 7 年前
unityjeffrey 0d67f311 changed ml agents to ml-agents 7 年前
unityjeffrey 19fb437a changed to Unity ML-Agents Toolkit (english) 7 年前
Deric Pang 8380f2f2 Moved curriculum code out of environment code. 7 年前
Deric Pang e580e544 Removing commented out code. 7 年前
Deric Pang db031b07 Updating tests for refactored curriculum learning. 7 年前
Deric Pang eb251008 Removing unnecessary import. 7 年前
Arthur Juliani 1eb701af Merge remote-tracking branch 'origin/develop' into develop-value-estimates-ppo 7 年前
Arthur Juliani f52d5a92 Merge remote-tracking branch 'origin/develop' into develop-runs 7 年前
GitHub ef3025e6 Merge pull request #1004 from Unity-Technologies/develop-runs 7 年前
GitHub 7d0990cf Fix MultiBrain bug that was introduced with the value estimates (#1018) 7 年前
Deric Pang de128fa1 Refactoring Curriculum tests and code. 6 年前
Deric Pang c6617b70 Multi-curriculum support added. 6 年前
Deric Pang c88c7e42 Fixing bugs, updating tests. 6 年前
Deric Pang 06eb8037 Renaming School to MetaCurriculum. 6 年前
Deric Pang e678e691 Addressing Vince's offline comments. 6 年前
Deric Pang ca54fc4f Adding back import that was accidentally removed. 6 年前
Deric Pang 9d9c91e4 Fixed TensorBoard lesson logging. 6 年前
Deric Pang 70308432 Adding space in metacurriculum error message. 6 年前
Deric Pang 4429077f Improving MetaCurriculum initialization. 6 年前
Deric Pang 822d329a Fixing bug when no curriculum folder is passed. 6 年前
Deric Pang 032446de Trainer controller lines wrapped. 6 年前
Deric Pang bb8e74f9 Helper func for incrementing lessons and resetting. 6 年前
Arthur Juliani 9e8049f0 Will now print summaries even when not training or when training is over (#1020) 6 年前
GitHub 9538d699 Move seed randomization to learn.py (#1071) 6 年前
Deric Pang 6eba6940 Merge remote-tracking branch 'upstream/develop' into develop-trainer-controller-cleanup 6 年前
Deric Pang 634280a6 Fixed imports, all tests are passing. 6 年前
GitHub c8371e3b Print summaries at inference (#1143) 6 年前
GitHub fbf92810 Refactor Trainers to use Policy (#1098) 6 年前
GitHub 10d2a19d Release v0.5 (Develop) (#1203) 6 年前
GitHub 6430fc86 Changing learn.py log messages. (#1159) 6 年前
GitHub a6f45b76 Fixing learn.py, trainer_controller.py, and Docker (#1164) 6 年前
GitHub 29084e77 Curriculum learning reward thresholding bug fix (#1141) 6 年前
GitHub 6b04b516 Consistent string style in trainer_controller.py (#1177) 6 年前
GitHub 2af80543 Add fix for multiple instances on a single GPU (#1192) 6 年前
GitHub af7de3ca Fix bug when academy max steps is set to nonzero value. (#1195) 6 年前
GitHub d2c320dd Remove graph scope (#1205) 6 年前
GitHub 3c9603d6 Demonstration Recorder (#1240) 6 年前
GitHub 78374601 vince's fix for model step (#1329) 6 年前
eshvk 4a96b14d Fixes to container workflow for GCP 6 年前
eshvk 3755a211 Refactor and clean up code 6 年前
GitHub cc083fd8 fixed the windows ctrl-c bug (#1558) 6 年前
GitHub 517e3a0a Remove env creation logic from TrainerController (#1562) 6 年前
Vincent-Pierre BERGES 4a6ae4e0 Barracuda integration into ML-Agents (#1557) 6 年前
GitHub c258b1c3 Move 'take_action' into Policy class (#1669) 6 年前
eshvk cc9bdf17 Added logging per Brain of time to update policy, time elapsed during training, time to collect experiences, buffer length, average return 6 年前
eshvk fb04c40c Reorganize to make metrics collection more accurate 6 年前
GitHub 93760bc4 Adds SubprocessUnityEnvironment for parallel envs (#1751) 6 年前
Jonathan Harper 7a0d1531 Fix subprocess model saving on Windows 6 年前
Jonathan Harper e91e847c Fix '--slow' flag after environment updates 6 年前
eshvk ef8009d9 Python code reformat via [`black`](https://github.com/ambv/black). 6 年前
Jonathan Harper d9a7e5b6 Fix failure on Academy Done() with parallel envs 6 年前
GitHub 2671e1a0 Enable mypy in precommit checks (#2177) 6 年前
Jonathan Harper 177ee5b8 Remove unused "last reward" logic, TF nodes 6 年前
GitHub b05c9ac1 Add environment manager for parallel environments (#2209) 6 年前
GitHub 966d8efb Remove "external_brains" arg for TrainerController (#2213) 6 年前
Chris Elion af4699ac Fix reference to external_brains in TrainerController (#2237) 6 年前
GitHub 84d9d622 python timers (#2180) 6 年前
GitHub 19283bfa Very simple environment for testing (#2266) 5 年前
GitHub 9eb3f049 Cleanup unused code in TrainerController (#2315) 5 年前
Ervin T a46f3faa Enable generalization training (#2232) 5 年前
Jonathan Harper 98297be9 Fix training not quitting when play button is unchecked (#2376) 5 年前
GitHub a9fe719c Add Multi-GPU implementation for PPO (#2288) 5 年前
GitHub 30930383 Move trainer initialization into a utility function (#2412) 5 年前
sankalp04 121221f2 Adding new command line arguments 5 年前
sankalp04 dfc8885d Allow generalization training with specified arguments of min_reward and min_lesson_length 5 年前
sankalp04 0b006719 Incorporate generalization checks for resetting parameters in take_step 5 年前
sankalp04 f331e5b7 Rebase develop 5 年前
Jonathan Harper 2f083c8a Renamed "StepInfo" to "EnvironmentStep" 5 年前
GitHub 67d754c5 Fix flake8 import warnings (#2584) 5 年前
Chris Elion 43e23941 rough pass at tf2 support, needs cleanup 5 年前
Chris Elion 806c77e4 centralize tensorflow imports 5 年前
GitHub 39f280d6 Develop spawn brains (#2676) 5 年前
Chris Elion 254c7d86 Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
GitHub b95c4d1d check for unecessary list comprehensions (#2707) 5 年前
GitHub 5d3e05d1 Fix "memory leak" during inference (#2722) 5 年前
Chris Elion 3d8a70fb Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
Chris Elion 73a346cb cleanup 5 年前
Andrew Cohen 13fe9cf8 Bubbled up indexing of AllBrainInfo to trainer controller from trainers 5 年前
Andrew Cohen e96b80db recieves brain_name and identifier on python side 5 年前
GitHub d6f69c1f handle null action outputs (#2988) 5 年前
Ervin Teng 3434352a Non-working commit 5 年前
Ervin Teng 17dca3ce Another nonworking commit 5 年前
Ervin Teng 1e36028d Runs but doesn't do anything yet 5 年前
Ervin Teng 34f9577c Merge branch 'develop' into develop-agentprocessor 5 年前
GitHub 8ec5ab62 Develop side channels: migrate reset parameters (#2990) 5 年前
Ervin Teng 2c9376bc Convert to trajectory 5 年前
Ervin Teng 9e661f0c Looks like it's training 5 年前
Ervin Teng 9c5fdd31 Stats reporting is working 5 年前
Andrew Cohen 5097bcc0 recieves brain_name and identifier on python side 5 年前
GitHub e7bf6fff Close environment if step raises an exception. (#3043) 5 年前
Ervin Teng 88b1123a Merge branch 'master' of github.com:Unity-Technologies/ml-agents into develop-agentprocessor 5 年前
Andrew Cohen 2b192bc3 trainer_controller expects name_behavior_ids 5 年前
Andrew Cohen 8578b0b7 add_policy and create_policy separated 5 年前
Andrew Cohen ef2dfd4c adjusting tests to expect trainer.add_policy to be called 5 年前
GitHub 36048cb6 Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
GitHub 42bea858 Improve mypy coverage by adding --namespace-packages (#3049) 5 年前
Andrew Cohen bd5e8434 fixed naming name_behavior_id 5 年前
Andrew Cohen 614d276f recieves brain_name and identifier on python side 5 年前
Ervin Teng 40bbe173 Better decoupling for agent processor 5 年前
GitHub 2c3794a6 handle mismatch between brain and metacurriculum (#3034) 5 年前
Chris Elion fdc810ff move (first pass) 5 年前
GitHub 58b6c7c2 Rename mlagents.envs to mlagents_envs (#3083) 5 年前
Ervin Teng 97d66e71 Remove BootstrapExperience 5 年前
Andrew Cohen 46f8f077 trainer_controller expects name_behavior_ids 5 年前
Andrew Cohen d1edbf43 add_policy and create_policy separated 5 年前
Andrew Cohen 70357569 adjusting tests to expect trainer.add_policy to be called 5 年前
GitHub 2fd305e7 Move add_experiences out of trainer, add Trajectories (#3067) 5 年前
Andrew Cohen e67e866e fixed naming name_behavior_id 5 年前
Ervin Teng c330f6f6 Merge branch 'master' into develop-agentprocessor 5 年前
Andrew Cohen de902fbb passes all pytest and C# tests 5 年前
GitHub 2ac242f7 Remove TrainerMetrics and add CSVWriter using new StatsWriter API (#3108) 5 年前
GitHub 0b5b1b01 Develop magic string + trajectory (#3122) 5 年前
Andrew Cohen 082789ea Merge branch 'master' into develop-magic-string 5 年前
Ervin Teng bad47dad Allow None max steps 5 年前
Ervin Teng 1bd791e5 Merge branch 'master' into develop-agentprocessor 5 年前
Ervin Teng abc8ca9a Fix tests 5 年前
GitHub 7fbf6b1d add flake8-bugbear (#3137) 5 年前
Andrew Cohen 654b0c79 Merge branch 'master' into develop-magic-string 5 年前
GitHub c6152459 Allow curricula to be created without files (#3145) 5 年前
GitHub bec2e8f0 Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113) 5 年前
Andrew Cohen fc485077 fixed more ci problems/removed self.policies 5 年前
Ervin Teng db743971 Move private methods out of trainer, simplify interface 5 年前
Andrew Cohen c8514c18 Merge branch 'master' into develop-magic-string 5 年前
GitHub 45010af3 Add stats reporter class and re-enable missing stats (#3076) 5 年前
GitHub bed7debf Fix issue with different decision intervals for different brains (#3181) 5 年前
Ervin Teng 3d25f9d2 Merge branch 'master' into develop-agentprocessor 5 年前
GitHub d985dded Merge branch 'master' into merge-release-0.13.0 5 年前
Andrew Cohen 4c260917 fix flake merge conflicts with master 5 年前
GitHub 4c241a80 Only send previous action and current BrainInfo (#3187) 5 年前
GitHub f058b18c Replace BrainInfos with BatchedStepResult (#3207) 5 年前
GitHub ca96b293 Move advance() logic for environment manager out of trainer_controller (#3234) 5 年前
GitHub 14193ada Self-play for symmetric games (#3194) 5 年前
GitHub 65dbe0ec Move processing of steps after reset to advance() (#3271) 5 年前
GitHub be14dd42 Make the timer output format consistent (#3472) 5 年前
Andrew Cohen bd78ec40 self-play assym hacked branch 5 年前
Anupam Bhatnagar e8e0078e first commit 5 年前
Anupam Bhatnagar 07b15ae7 [skip-ci] small refactors 5 年前
Chris Elion 0d65c600 top-level timers to see where time is going 5 年前
Chris Elion a5dd261b make sure top-level timer is closed before writing 5 年前
GitHub 25cc9f15 [change] Move hyperparameter printing entirely into StatsWriters (#3630) 5 年前
GitHub ec278616 Hotfixes for Release 0.15.1 (#3698) 5 年前
Andrew Cohen 9f09a65d team id centric ghost trainer 5 年前
Ervin Teng 3deb8e30 Make trainer in separate threads 5 年前
Ervin Teng 93351d30 Fix comments 5 年前
GitHub 807a1441 Raise exceptions from environment subprocesses (#3680) 5 年前
GitHub 4ecd6ad3 Fix how we set logging levels (#3703) 5 年前
Andrew Cohen 62c87031 Merge branch 'master' into self-play-mutex 5 年前
Andrew Cohen 59b88be6 Merge branch 'master' into self-play-mutex 5 年前
Ervin Teng 06fa3d39 Merge branch 'master' into develop-sac-apex 5 年前
Anupam Bhatnagar 50e52d9c Merge branch 'master' into distributed-training 5 年前
Andrew Cohen 3de78baa wrapped trainer has internal policy ghost 5 年前
Andrew Cohen 3013774b alternative to internal-policy fix 5 年前
Ervin Teng ed06f37c Ability to disable threading 5 年前
Anupam Bhatnagar 001fce2a first commit 5 年前
Ervin Teng 5e980ec1 Merge branch 'master' into develop-sac-apex 5 年前
Ervin Teng d1fed8ae Remove empty_queue interface 5 年前
Ervin Teng 9fe104d6 Make threading disable-able per trainer 5 年前
Ervin Teng 92158d54 Remove threaded from trainer_controller 5 年前
Ervin Teng 8d2434c2 kill trainer threads when training finishes 5 年前
Ervin Teng ebed4f51 Only create/start thread for new trainers 5 年前
Ervin Teng 392fcb4e Fix stall in ghost trainer non-threaded 5 年前
Andrew Cohen ddb6787c hard reset when team changes 5 年前
GitHub 4092d937 [Bug fix] Hard reset when team changes (#3870) 5 年前
GitHub 232519e4 [refactor] Move output artifacts to a single results/ folder (#3829) 5 年前
GitHub ebe12502 [bug-fix] Fix exception thrown when quitting in-editor training from editor (#3885) 5 年前
GitHub d8b93f8f [Bug fix] Hard reset when team changes (#3870) (#3899) 5 年前
GitHub f501c395 Fix timers when using multithreading. (#3901) 5 年前
Chris Elion 68b68396 Merge remote-tracking branch 'origin/master' into release_1_to_master 5 年前
Christopher Goy ba80b292 format files with pre-commit. 4 年前
GitHub e92b4f88 [refactor] Structure configuration files into classes (#3936) 5 年前
Andrew Cohen 4464ca46 ignoring commit checks 5 年前
GitHub f5435876 [refactor] Store and restore state along with checkpoints (#4025) 5 年前
Andrew Cohen e7750fc9 Merge branch 'master' into develop-sampler-refactor 5 年前
GitHub 09853e13 [refactor] Move checkpoint saving into trainer (#4034) 5 年前
Andrew Cohen 22786526 Merge branch 'master' into asymm-envs 5 年前
PSankalp Patro 45c4ea36 Save checkpoint files as .nn files in checkpoint directory 5 年前
Andrew Cohen c0f7052b Merge branch 'master' into develop-sampler-refactor 5 年前
Andrew Cohen 34ecc7e6 Merge branch 'master' into asymm-envs 5 年前
Anupam Bhatnagar 4afd8f92 first commit 5 年前
Jonathan Harper 80127232 Convert checkpoints to .nn format 5 年前
Anupam Bhatnagar 24d5f881 first commit 5 年前
GitHub a28e2767 Update add-fire to latest master, including Policy refactor (#4263) 4 年前
GitHub 3bcb029b [refactor] Remove BrainParameters from Python code (#4138) 5 年前
GitHub 8eefdcd3 Refactor of Curriculum and parameter sampling (#4160) 5 年前
GitHub 84440f05 Convert checkpoints to .NN (#4127) 5 年前
GitHub 1f5eb9da add pyupgrade to pre-commit and run (#4239) 4 年前
GitHub 2c64d623 don't try/except for control flow (#4251) 4 年前
Anupam Bhatnagar dbd5dc04 adding rank to ml-agents 4 年前
GitHub a74c7bc5 TensorBoard Lesson -> Lesson Number (#4347) 4 年前
Anupam Bhatnagar abc1220f Merge branch 'master' into global-variables 4 年前
GitHub 2332bc32 Add fire to test_simple_rl.py (#4378) 4 年前
Anupam Bhatnagar 5e8aa485 renaming file from globals.py to global_values.py 4 年前
Scott Jordan d695c044 initial addition of active learning (incomplete) 4 年前
Anupam Bhatnagar 1f60979f [skip ci] change self.rank to global_values.get_rank() 4 年前
Scott Jordan 9f3d3428 Merge branch 'master' into active-variablespeed 4 年前
Anupam Bhatnagar f4f1a8d9 merge master into trainer-plugin branch 4 年前
Scott Jordan 56745026 Initial commit of running active learning code 4 年前
Scott Jordan 78f8a9a2 Updated task manager 4 年前
Scott Jordan 87969325 added histogram recorded, fixed active learning bug 4 年前
GitHub 1076d275 Remove unused methods in trainer_controller.py (#4418) 4 年前
vincentpierre d137feab using torch.set_num_threads 4 年前
GitHub 6f534366 Add torch_utils class, auto-detect CUDA availability (#4403) 4 年前
vincentpierre c78639a0 - 4 年前
Ervin Teng 4b3f5f77 Add pympler 4 年前
GitHub c188781b [life improvement] Moving Python files around (#4531) 4 年前
GitHub a690af74 [refactor] Make PyTorch the default and TensorFlow optional (#4517) 4 年前
Ervin Teng 3b15cc32 Multiprocessing but Stats are quite broken 4 年前
vincentpierre b863af57 Removing TensorFlow Trainers 4 年前
vincentpierre 713e65fb removing tensorflow testing for pytest and yamato 4 年前
Andrew Cohen 5bbe796b update soccer raycasts 4 年前
Andrew Cohen 34420044 fix trainer c and soccer config 4 年前
Andrew Cohen c72e00c9 fix multiple policy issue 4 年前
GitHub d8835857 [MLA-1540] Training Analytics (#4780) 4 年前
GitHub f16ce486 Update v2-staging from main (March 15) (#5123) 4 年前
GitHub 9a3600d5 Logging lesson number at the begining of training (#5199) 4 年前
GitHub 2e19759c Turning some logger.info into logger.debug and remove some logging overhead when not using debug (#5211) 4 年前