GitHub
14193ada
Self-play for symmetric games ( #3194 )
5 年前
Ervin Teng
48b39b80
Fix ghost trainer and all tests
5 年前
Ervin Teng
dcbb90e1
Fix graph init in ghost trainer
5 年前
GitHub
34792205
adding init to ghost trainer directory ( #3381 )
5 年前
GitHub
25c41f83
adding init to ghost trainer directory ( #3381 ) ( #3382 )
5 年前
Anupam Bhatnagar
c70d0243
[bug-fix] Empty ignored trajectory queues, make sure queues don't overflow ( #3451 )
5 年前
Ervin Teng
5ef902bf
Merge branch 'master' into develop-splitpolicyoptimizer
5 年前
GitHub
6876a1d6
[bug-fix] Empty ignored trajectory queues, make sure queues don't overflow ( #3451 )
5 年前
Andrew Cohen
e4d776c3
Merge branch 'master' into soccer-fives
5 年前
Ervin Teng
bcc25d59
Merge branch 'master' into develop-splitpolicyoptimizer
5 年前
GitHub
472f9f0e
Merge branch 'master' into develop-badEnvReturnCode
5 年前
Ervin Teng
88998fc9
Add add_policy docstrings
5 年前
GitHub
c145e75b
Split Policy and Optimizer, common Policy for PPO and SAC ( #3345 )
5 年前
Andrew Cohen
5b0aca29
Merge branch 'master' into soccer-fives
5 年前
Ervin Teng
1156b9b3
Merge branch 'develop-splitpolicyoptimizer' into develop-removeactionholder
5 年前
Anupam Bhatnagar
e04fcd71
Merge branch 'master' into master-into-release-0.14.1
5 年前
Andrew Cohen
bd78ec40
self-play assym hacked branch
5 年前
Andrew Cohen
8fe1a27d
fixed save_snapshot
5 年前
Andrew Cohen
30725c27
2v1 soccer config and env
5 年前
Andrew Cohen
94654de4
ghost controller
5 年前
GitHub
e4177de0
[change] Organize trainer files a bit better ( #3538 )
5 年前
Andrew Cohen
573b1f6d
Merge branch 'master' into soccer-fives
5 年前
Anupam Bhatnagar
f4dbedcf
removed extraneous logging imports and loggers
5 年前
GitHub
86141eee
Merge pull request #3560 from Unity-Technologies/new-logger
Add timestamps to logs
5 年前
GitHub
e3af96ca
Merge branch 'master' into develop-demo-load-seek
5 年前
Andrew Cohen
b1cfa74d
Merge branch 'master' into develop-test-imitation
5 年前
GitHub
ec278616
Hotfixes for Release 0.15.1 ( #3698 )
* [bug-fix] Increase height of wall in CrawlerStatic (#3650 )
* [bug-fix] Improve performance for PPO with continuous actions (#3662 )
* Corrected a typo in a name of a function (#3670 )
OnEpsiodeBegin was corrected to OnEpisodeBegin in Migrating.md document
* Add Academy.AutomaticSteppingEnabled to migration (#3666 )
* Fix editor port in Dockerfile (#3674 )
* Hotfix memory leak on Python (#3664 )
* Hotfix memory leak on Python
* Fixing
* Fixing a bug in the heuristic policy. A decision should not be requested when the agent is done
* [bug-fix] Make Python able to deal with 0-step episodes (#3671 )
* adding some comments
Co-authored-by: Ervin T <ervin@unity3d.com>
* Remove vis_encode_type from list of required (#3677 )
* Update changelog (#3678 )
* Shorten timeout duration for environment close (#3679 )
The timeout duration for closing an environment was set to the
same duration as the timeout when waiting ...
5 年前
Andrew Cohen
53bea15c
Merge branch 'master' into soccer-fives
5 年前
Andrew Cohen
ac261e36
Merge branch 'master' into self-play-mutex
5 年前
GitHub
6709a9bf
[change] Clean up trainer interface, clean up GhostTrainer stats ( #3634 )
5 年前
Andrew Cohen
eefc4811
Merge branch 'master' into self-play-mutex
5 年前
Andrew Cohen
9f09a65d
team id centric ghost trainer
5 年前
Andrew Cohen
79076b70
ELO calculation done in ghost controller
5 年前
Andrew Cohen
03b40795
removed opponent elo from stat collection
5 年前
Andrew Cohen
579bbd88
passing all tests locally
5 年前
Andrew Cohen
66b505c3
fixed controller behavior when first team discovered isnt 0
5 年前
Andrew Cohen
1a6e99bb
save step on trainer step count/swap on ghost
5 年前
Andrew Cohen
072b4135
soccer 2v1 on the cloud
5 年前
Andrew Cohen
1269b555
docstrings/ghost_swap -> team_change
5 年前
Andrew Cohen
b42c9482
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
Andrew Cohen
b15a8b75
docstrings for all ghost trainer functions
5 年前
Andrew Cohen
cbba8f52
SELF-PLAY NOW SUPPORTS MULTIAGENT TRAINERS
5 年前
Andrew Cohen
31ef5a84
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
Andrew Cohen
81a141c0
next learning team from get step
5 年前
Andrew Cohen
15770bec
comment for self.ghost_step
5 年前
Andrew Cohen
80fd858a
ghost->get_step
5 年前
Andrew Cohen
052a24a0
fixed export so both teams have current model
5 年前
Andrew Cohen
a13f107f
updated self-play doc for asymmetric games/changed current_self->current_best
5 年前
Andrew Cohen
88b8a922
count trainer steps in controller by team id
5 年前
Andrew Cohen
c05d6c49
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
Andrew Cohen
60ea278d
added team_change as a yaml config
5 年前
Andrew Cohen
bc611906
removed team-change CLI
5 年前
Andrew Cohen
42518d84
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
Andrew Cohen
19552661
added team_change as a yaml config
5 年前
Andrew Cohen
650ec121
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
Andrew Cohen
74d37a11
removed not max step reached as condition for ELO
5 年前
Andrew Cohen
0d460514
warning for team change hyperparam
5 年前
Andrew Cohen
aa18bef6
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
Andrew Cohen
93d344ff
simple rl asymm ghost tests
5 年前
Andrew Cohen
c60d0c5a
renamed controller methods/doc fixes
5 年前
GitHub
4ecd6ad3
Fix how we set logging levels ( #3703 )
* cleanup logging
* comments and cleanup
* pylint, gym
5 年前
Andrew Cohen
345fa382
current_best_ratio -> latest_model_ratio
5 年前
Andrew Cohen
c7a34413
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
Andrew Cohen
59b88be6
Merge branch 'master' into self-play-mutex
5 年前
GitHub
9cbc3fa2
Asymmetric self-play ( #3653 )
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
335e70ea
using mlagents_env.logging instead of logging
5 年前
GitHub
9c8142c2
Fix save snapshot bug in ghost trainer ( #3722 )
5 年前
Andrew Cohen
3de78baa
wrapped trainer has internal policy ghost
5 年前
Andrew Cohen
b9179f0f
fixed order of load weight/create tf graph in add_policy
5 年前
Andrew Cohen
3013774b
alternative to internal-policy fix
5 年前
Ervin Teng
ed06f37c
Ability to disable threading
5 年前
Ervin Teng
971e4b2d
Don't block when disabling threading
5 年前
Andrew Cohen
573f80cd
added to mig doc/address comments
5 年前
Andrew Cohen
189b4765
remove incorrect docstring
5 年前
Ervin Teng
d1895272
Fix ghost trainer locking up
5 年前
Andrew Cohen
3a1912c1
raise warning when latest_model_ratio not btwn 0, 1
5 年前
GitHub
b841c9ab
Wrapped trainer has internal policy in GhostTrainer
5 年前
Andrew Cohen
930d6fa3
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
Andrew Cohen
fc732b29
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
GitHub
aae58330
Merge branch 'master' into develop-add-inference-examples
5 年前
Andrew Cohen
b0c506a6
Merge branch 'soccer-2v1' into asymm-envs
5 年前
Andrew Cohen
c07e0fce
Merge branch 'soccer-2v1' into asymm-envs
5 年前
Ervin Teng
5e980ec1
Merge branch 'master' into develop-sac-apex
5 年前
Andrew Cohen
c79f9f02
Merge branch 'self-play-mutex' into soccer-2v1
5 年前
Andrew Cohen
ed1bda98
Merge branch 'master' into soccer-2v1
5 年前
Ervin Teng
d1fed8ae
Remove empty_queue interface
5 年前
Ervin Teng
e90ef688
Revert to get_nowait method in AgentManagerQueue
5 年前
Andrew Cohen
413633dc
Merge branch 'master' into soccer-2v1
5 年前
Andrew Cohen
02d26c3f
Merge branch 'soccer-2v1' into asymm-envs
5 年前
Andrew Cohen
de0656b6
Merge branch 'internal-policy-ghost' into soccer-2v1
5 年前
Andrew Cohen
4bc36520
Merge branch 'soccer-2v1' into asymm-envs
5 年前
Andrew Cohen
a3383ee9
Merge branch 'soccer-2v1' into asymm-envs
5 年前
Andrew Cohen
85304aff
Merge branch 'soccer-2v1' into asymm-envs
5 年前
Andrew Cohen
89db8428
Merge branch 'internal-policy-ghost-alternate' into soccer-2v1
5 年前
Andrew Cohen
26c0033c
Merge branch 'soccer-2v1' into asymm-envs
5 年前
GitHub
2e939d50
Clean up and fix save and load in ghost ( #3797 )
5 年前
Arthur Juliani
3769d943
Merge remote-tracking branch 'origin/master' into develop-add-fire
5 年前
GitHub
4d23200b
[refactor] Run Trainers in separate threads ( #3690 )
5 年前
Ervin Teng
9cd2c034
Merge branch 'master' of github.com:Unity-Technologies/ml-agents into develop-sac-apex
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
Arthur Juliani
212e2d1d
Merge remote-tracking branch 'origin/master' into develop-add-fire
5 年前
GitHub
d8b93f8f
[Bug fix] Hard reset when team changes ( #3870 ) ( #3899 )
5 年前
Andrew Cohen
9d5d6fa7
Merge branch 'master' into asymm-envs
5 年前
vincentpierre
c34dd5b6
Merge branch 'master' into develop-gym-wrapper
5 年前
Andrew Cohen
a2f8319a
Merge branch 'master' into asymm-envs
5 年前
Christopher Goy
ba80b292
format files with pre-commit.
4 年前
GitHub
f7373172
Merge pull request #4385 from Unity-Technologies/release_2_verified-barracuda-1.0.2
update verified brach with barracuda 1.0.2
4 年前
Ruo-Ping Dong
2ca79207
[bug-fix] Don't load non-wrapped policy ( #4593 )
* Always initialize non-wrapped policy
* Load ghosted policy
* Update changelog
* Resume test
* Add test
* Add torch test and fix torch.
4 年前
GitHub
e92b4f88
[refactor] Structure configuration files into classes ( #3936 )
5 年前
GitHub
5cce69ae
add "the the" to precommit spell check ( #4059 )
5 年前
Andrew Cohen
e7750fc9
Merge branch 'master' into develop-sampler-refactor
5 年前
Andrew Cohen
e0aa5cee
Merge branch 'develop-team-change-reset' into asymm-envs
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
Andrew Cohen
c0f7052b
Merge branch 'master' into develop-sampler-refactor
5 年前
GitHub
a1c63c4b
Release 3 Cherry-pick bug-fixes and doc changes from master ( #4102 )
* [bug-fix] Fix regression in --initialize-from feature (#4086 )
* Fixed text in GettingStarted page specifying the logdir for tensorboard. Before it was in a directory summaries which no longer existed. Results are now saved to the results dir. (#4085 )
* [refactor] Remove nonfunctional `output_path` option from TrainerSettings (#4087 )
* Reverting bug introduced in #4071 (#4101 )
Co-authored-by: Scott <Scott.m.jordan91@gmail.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
5 年前
GitHub
8a49e8e0
[refactor] Remove nonfunctional `output_path` option from TrainerSettings ( #4087 )
5 年前
Arthur Juliani
9724c9ac
Merge master
5 年前
Jonathan Harper
80127232
Convert checkpoints to .nn format
Fixed style
Fixed more style
Nit changes
Fixed signature
Convert checkpoints to .nn format
Fixed style
Nit changes
Fixed tests, checkpoint management and style
Check checkpoint management
Modify statement on artifacts
Nit changes
Fixed signature
Nit changes
Fixed signature
Fixed tests, checkpoint management and style
Check checkpoint management
Modify statement on artifacts
5 年前
GitHub
a28e2767
Update add-fire to latest master, including Policy refactor ( #4263 )
* Update Dockerfile
* Separate send environment data from reset (#4128 )
* Fixed a typo on ML-Agents-Overview.md (#4130 )
Fixed redundant "to" word from the sentence since it is probably a typo in document.
* Updated the badge’s link to point to the newest doc version
* Replaced all of the doc to release_3_doc
* Fix 3DBall and 3DBallHard SAC regressions (#4132 )
* Move memory validation to settings
* Update docs
* Add settings test
* Update to release_3 in installation.md (#4144 )
* rename to SideChannelManager +backcompat (#4137 )
* Remove comment about logo with --help (#4148 )
* [bugfix] Make FoodCollector heuristic playable (#4147 )
* Make FoodCollector heuristic playable
* Update changelog
* script to check for old release links and references (#4153 )
* Remove package validation suite from Project (#4146 )
* RayPerceptionSensor: handle empty and invalid tags (#4155...
4 年前
vincentpierre
599d7e9f
Merging master
5 年前
HH
7afa1761
Merge branch 'master' into hh/develop/ragdoll-updates
5 年前
GitHub
3bcb029b
[refactor] Remove BrainParameters from Python code ( #4138 )
5 年前
Ruo-Ping Dong
e06812aa
fix tests
4 年前
HH
0fdac847
Merge branch 'master' into hh/develop/crawler-ragdoll-updates
5 年前
GitHub
84440f05
Convert checkpoints to .NN ( #4127 )
This change adds an export to .nn for each checkpoint generated by
RLTrainer and adds a NNCheckpointManager to track the generated
checkpoints and final model in training_status.json.
Co-authored-by: Jonathan Harper <jharper+moar@unity3d.com>
5 年前
Arthur Juliani
6bee0fd1
Merge master
5 年前
GitHub
1f5eb9da
add pyupgrade to pre-commit and run ( #4239 )
5 年前
GitHub
129f9ddc
[MLA-427] make pyupgrade convert f-strings too ( #4244 )
* make pyupgrade convert f-strings too
5 年前
GitHub
2c64d623
don't try/except for control flow ( #4251 )
4 年前
Andrew Cohen
d8c123a0
Merge branch 'master' into sensitivity
4 年前
GitHub
beb5aca5
[refactor] Make classes except Optimizer framework agnostic ( #4268 )
4 年前
Andrew Cohen
06e4356c
Merge branch 'master' into sensitivity
4 年前
Arthur Juliani
1a123641
Merge remote-tracking branch 'origin/master' into r5-master
4 年前
Ruo-Ping Dong
95858e25
update saver interface and add tests
4 年前
Ruo-Ping Dong
523248be
update
4 年前
HH
8eaddb61
Merge branch 'master' into hh/develop/loco-walker-variable-speed
4 年前
GitHub
25dc8c3d
Add Saver Class to handle all save/load/checkpoint/export work ( #4323 )
4 年前
Ervin Teng
d65a9326
Merge branch 'master' into develop-add-fire-mm3
4 年前
GitHub
bd6bcd2f
Merge master and add Saver class for save/load checkpoints
4 年前
Ervin Teng
42e25b25
Merge branch 'develop-add-fire' into develop-add-fire-memoryclass
4 年前
Christopher Goy
5a233353
Merge remote-tracking branch 'origin/master' into release_6-to-master
4 年前
Andrew Cohen
a65d08c7
ghost trainer tests
4 年前
GitHub
49545ce1
Pytorch ghost trainer ( #4370 )
4 年前
GitHub
1955af9e
[feature] Add experimental PyTorch support ( #4335 )
* Begin porting work
* Add ResNet and distributions
* Dynamically construct actor and critic
* Initial optimizer port
* Refactoring policy and optimizer
* Resolving a few bugs
* Share more code between tf and torch policies
* Slightly closer to running model
* Training runs, but doesn’t actually work
* Fix a couple additional bugs
* Add conditional sigma for distribution
* Fix normalization
* Support discrete actions as well
* Continuous and discrete now train
* Mulkti-discrete now working
* Visual observations now train as well
* GRU in-progress and dynamic cnns
* Fix for memories
* Remove unused arg
* Combine actor and critic classes. Initial export.
* Support tf and pytorch alongside one another
* Prepare model for onnx export
* Use LSTM and fix a few merge errors
* Fix bug in probs calculation
* Optimize np -> tensor operations
* Time action sample funct...
4 年前
Ruo-Ping Dong
c47ffc20
Rename saver
4 年前
GitHub
48f217b9
Rename Saver to ModelSaver ( #4402 )
Rename Saver to ModelSaver to avoid confusion with tf.Saver
4 年前
Anupam Bhatnagar
f4f1a8d9
merge master into trainer-plugin branch
4 年前
Ruo-Ping Dong
fd1dc3a6
Merge branch 'master' into develop-torch-omp
4 年前
Andrew Cohen
3997b14b
Merge branch 'master' into develop-hybrid-actions
4 年前
GitHub
b3bc7896
Cherrypick bug fixes to release_9_branch ( #4617 )
* [bug-fix] Don't load non-wrapped policy (#4593 )
* pin cattrs version
* cap PyTorch version
* use v2 action and pin python version (#4568 )
Co-authored-by: Ervin T <ervin@unity3d.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
4 年前
GitHub
b5dd43f2
[bug-fix] Don't load non-wrapped policy ( #4593 )
* Always initialize non-wrapped policy
* Load ghosted policy
* Update changelog
* Resume test
* Add test
* Add torch test and fix torch.
4 年前
vincentpierre
a3a9a56b
Merge branch 'exp-multi-head-attention' into exp-bullet-hell
4 年前
GitHub
23800f33
Merge branch 'master' into develop-action-spec
4 年前
Andrew Cohen
498b1ee6
Merge branch 'develop-action-buffer' into develop-hybrid-actions-singleton
4 年前
Ervin Teng
7087b7b3
Add cc to ghost trainer
4 年前
Ervin Teng
80598c48
Actually add comment to ghosttrainer
4 年前
Andrew Cohen
c72e00c9
fix multiple policy issue
4 年前
Ruo-Ping Dong
8ed14762
Merge branch 'develop-hybrid-actions-singleton' into develop-hybrid-actions-csharp
4 年前
Ervin Teng
4893f4b2
Fix team ELOs
4 年前
Ervin Teng
05db051e
Remove some unneeded changes
4 年前
GitHub
5022d710
Add additional logic to avoid load being called on every advance ( #4934 )
4 年前
Ruo-Ping Dong
c87bce9e
Merge branch 'master' into develop-base-teammanager
4 年前
Ervin Teng
219e773b
Merge branch 'develop-fix-lstms' into develop-critic-op-lstm
4 年前
vincentpierre
e1b94b8b
Merge branch 'master' into develop-var-len-obs-feature
4 年前
Andrew Cohen
dc8e8494
Merge branch 'master' into develop-critic-optimizer
4 年前
Chris Elion
e4f51ca7
Merge remote-tracking branch 'origin/master' into MLA-1734-demo-provider
4 年前
Ervin Teng
d4438878
Merge branch 'develop-base-teammanager' into develop-agentprocessor-teammanager
4 年前
Ervin Teng
e46a86ad
Merge branch 'master' into develop-superpush-int
4 年前
HH
15d512f9
Merge branch 'master' into hh/develop/dodgeball
4 年前
Ervin Teng
08db7c2f
Merge branch 'develop-agentprocessor-teammanager' into develop-coma2-trainer-mm
4 年前
Arthur Juliani
06c147f8
Merge remote-tracking branch 'origin/main' into goal-conditioning-new
# Conflicts:
# Project/Assets/ML-Agents/Examples/Crawler/Prefabs/CrawlerBase.prefab
# Project/Assets/ML-Agents/Examples/GridWorld/Prefabs/Area.prefab
# Project/Assets/ML-Agents/Examples/GridWorld/Scenes/GridWorld.unity
# Project/ProjectSettings/TagManager.asset
# com.unity.ml-agents/Runtime/Sensors/CameraSensor.cs
# com.unity.ml-agents/Runtime/Sensors/VectorSensor.cs
# ml-agents/mlagents/trainers/torch/networks.py
# ml-agents/mlagents/trainers/torch/utils.py
4 年前
Ervin Teng
c8137dcd
Merge branch 'main' into develop-superpush-int
4 年前
GitHub
f16ce486
Update v2-staging from main (March 15) ( #5123 )
4 年前
Christopher Goy
921ba4f0
Update v2-staging from main (March 15) ( #5123 )
4 年前
Chris Elion
970f1d40
Merge remote-tracking branch 'origin/v2-staging' into MLA-1634-ObservationSpec
4 年前
GitHub
8f35bdd3
POCA trainer ( #5005 )
Co-authored-by: Ervin Teng <ervin@unity3d.com>
Co-authored-by: Ruo-Ping Dong <ruoping.dong@unity3d.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
4 年前
Andrew Cohen
9e77d7e1
Merge branch 'main' into develop-soccer-groupman
4 年前
GitHub
39f8b6ac
add group done to ELO computation ( #5150 )
4 年前
GitHub
88ef8f25
R15 fix elo ( #5151 )
* add group done to ELO computation
* add not interrupted
4 年前
Ervin Teng
e1c23ad7
[ 🐛 🔨 ]Adding the ELO to the GlobalTrainingStatus ( #5202 )
* Adding the ELO to the GlobalTrainingStatus
* Update ml-agents/mlagents/trainers/ghost/trainer.py
Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>
Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>
(cherry picked from commit 9c3dc4542ce2fa35f25dfa7809a7e1c2ee06001e)
4 年前
Andrew Cohen
18be47e8
Merge branch 'main' into develop-soccer-groupman-mod
4 年前
GitHub
640b2e00
[ 🐛 🔨 ]Adding the ELO to the GlobalTrainingStatus ( #5202 )
* Adding the ELO to the GlobalTrainingStatus
* Update ml-agents/mlagents/trainers/ghost/trainer.py
Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>
Co-authored-by: andrewcoh <54679309+andrewcoh@users.noreply.github.com>
4 年前