29090047
Merge branch 'master' into develop-fix-mask
4 年前
e85d8e35
Added a comment and included the change of #4715 for simplicity
4 年前
acfaa516
Merge pull request #4716 from Unity-Technologies/develop-fix-validate-action
[Fix] Validate Action
4 年前
b3638ad6
Update prefabs
4 年前
93ac8654
[Fix] Validate Action
4 年前
90da7426
Fix masking for torch
4 年前
6b32ff21
Allow gridworld agent to have different goals
4 年前
a4c9f58e
Fix SubprocessEnvManager hanging on unexpected exceptions. ( #4699 )
* Add shutdown sentinel value to subprocess_env_manager.
* Add Sanity Check for Zombie Workers
4 年前
12e98345
Merge pull request #4703 from Unity-Technologies/develop-2d-obs-start
Allow 2d obs to be communicated
4 年前
46580ff9
Formatting
4 年前
03807d64
Some work for 2d obs
4 年前
559e0ee5
Fix set_action_for_agent ( #4691 )
* fixes
* Update CHANGELOG.md
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
4 年前
d816c37c
pin pip to 20.2 for now ( #4694 )
* pin pip to 20.2 for now
* add self to list of trigger files
4 年前
9cc20101
Fix heuristic example and some crefs ( #4690 )
4 年前
c11e939b
Add link to curriculum docs in learning environment design ( #4687 )
4 年前
d3348074
fix policy action_spec typo
4 年前
a7d04be6
Merge branch 'develop-hybrid-actions-singleton' into develop-hybrid-actions-csharp
4 年前
d7c3022d
Export separate nodes for continuous/discrete actions ( #4655 )
4 年前
1ab8871e
check tensor exist before access shape
4 年前
8ed14762
Merge branch 'develop-hybrid-actions-singleton' into develop-hybrid-actions-csharp
4 年前
b464678d
Merge pull request #4682 from Unity-Technologies/r10-to-master
Merging release 10 into master
4 年前
edc2ae2f
[bug-fix] Disable threading for self-play envs ( #4679 )
4 年前
4617a7b6
[bug-fix] Remove extra period ( #4674 )
* Remove extra period
* Update changelog
* Re add a period (#4676 )
* Adding a trailing period
* formating
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>
4 年前
1cac78e2
[Bug-fix] Remove extra directory created at checkpoint ( #4675 )
* [Bug-fix] Remove extra directory created at checkpoint
* removing os import
4 年前
de27d7a6
[bug-fix] Fix issue where NaNs are outputted by the policy when training Match3 ( #4664 )
* match3 settings
* Add epsilon to log
* Add another epsilon
* Revert match3 configs
* NaN-free masking method
* Add comment for paper
* Add comment for paper
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
4 年前
8175d558
[bug-fix] Fix BC module + action clipping ( #4667 )
4 年前
efdb1042
Add global lock for torch.onnx.export() ( #4659 )
4 年前
3ab45b3f
[bug-fix] Separate critic only for PPO ( #4661 )
4 年前
5ee6efb0
Make collab env harder
4 年前
078de517
🇺🇸 fix spelling 🇺🇸 ( #4663 )
4 年前
8cf87ed6
match3 settings
4 年前
e05e0aef
Collaborative walljump
4 年前
85a7c0f7
[bug-fix] Add clipping to PyTorch policy, fix initialization ( #4649 )
4 年前
87a7ccf8
use int64 steps, check for NaN actions ( #4607 )
* use int64 steps
* check for NaN actions
Co-authored-by: Ruo-Ping Dong <ruoping.dong@unity3d.com>
4 年前
4dd42642
Bumping versions on master for release_10 ( #4642 )
4 年前
7cdf3efe
Update CONTRIBUTING.md ( #4602 )
* Update CONTRIBUTING.md
Added note about env contributions
* removed trailing space
4 年前
8a1f0a8b
Updating the CHANGELOG on master before release 10 ( #4636 )
4 年前
d490bb44
add match3 to changelog ( #4635 )
4 年前
1b933a0a
Add Graphics to the Match3 env ( #4627 )
* first pass - matching and gravity work
* valid moves WIP
* move enumeration, simple checking
* move detection
* fix up/down directions
* actuator and heuristic
* sensor
* reset if no moves
* add masking, retrain
* cleanup
* config update
* optionally force heuristic mode
* compressed observations, reset board if no moves
* TFModel meta files
* WIP abstract
* random move heuristic
* rename Move fields, migrate IsValid logic
* comments
* reduce dependency on Match3Agent
* abstractBoard as monobehavior
* move actuator to extensions
* move sensor to extensions
* update components in scene
* undo accidental checkins
* drawing cleanup, custom maxMoves logic
* meta file
* prefab, use 8 agents
* different behaviors
* timers, early out
* unit tests
* docs
* Apply suggestions from code review
Co-authored-by: Vincent-Pierre BERGES <vincentpierre@unity3d.com>...
4 年前
8669e389
Refactor BarracudaModel loader checks ( #4629 )
* move model methods to BarracudaModelExtensions
* add method to check expected tensors in extensions
4 年前
90a9d214
Match3 example ( #4515 )
4 年前
fb4661b0
Merge release_9_branch to master ( #4623 )
4 年前
96452986
Initial commit for multi head attention
4 年前
95efe03b
[MLA-1519] Don't mark action_probs as an output node. ( #4613 )
* remove action_probs from output nodes
* changelog
* pin cattrs upper version
* print pip freeze results
* add comment about cattrs version
4 年前
64e998a2
[bug-fix] Use float64 when converting np.ndarray to torch.tensor, cap Torch version to 1.7.x ( #4610 )
* Use float64 in GAIL tests
* Use float32 when converting np arrays by default
* Enforce torch 1.7.x or below
* Add comment about Windows install
* Adjust tests
4 年前
6ce2434d
Fix typo in URL ( #4604 )
4 年前
a4ba90ec
[bug-fix] Fix ONNX export/Barracuda import for continuous actions ( #4608 )
* Use torch.ones rather than expand
* use tf.cat instead of tf.expand for Barracuda
* fix error msg handling
* handle loading exception
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
4 年前
cb8e4d25
Add ActionSpec ( #4586 )
Co-authored-by: Ervin T <ervin@unity3d.com>
4 年前
0e91ff08
Reword readme ( #4603 )
4 年前
e0ef30a5
[bug-fix] Change entropy computation and loss reporting in Torch to match TF ( #4538 )
* Proper dimensions for entropy, sum before bonus in PPO
* Make entropy reporting same as TF
* Always use separate critic
* Revert to shared
* Remove unneeded extra line
* Change entropy shape in test
* Change another entropy shape
* Add entropy summing to evaluate_actions
* Add notes about torch.abs(policy_loss)
4 年前
vincentpierre
GitHub
Arthur Juliani
Ruo-Ping Dong
Ervin Teng
Chris Elion