0476c599
Remove print statement
4 年前
68169434
Fix discrete actions and GridWorld
4 年前
0d80d87a
Fix for discrete actions ( #4181 )
4 年前
5d33aca7
Remove double setting
4 年前
b6dfb4ac
Fix ResNet
4 年前
6408fd4e
Fix bug in pdf function
4 年前
e14eb72b
Fix some issues with pdf
4 年前
46874cc7
ONNX exporting
4 年前
9724c9ac
Merge master
4 年前
28e095e0
Merge remote-tracking branch 'origin/master' into develop-add-fire
4 年前
039f545a
Small performance improvement during inference
4 年前
c02e75d6
Time action sample function
4 年前
3eef9d78
Optimize np -> tensor operations
4 年前
b7be7f04
Fix bug in probs calculation
4 年前
2b3a6347
Merge remote-tracking branch 'origin/master' into develop-add-fire
4 年前
be7e55e1
Use LSTM and fix a few merge errors
4 年前
89ad3020
Merge remote-tracking branch 'origin/master' into develop-add-fire
# Conflicts:
# ml-agents/mlagents/trainers/policy/tf_policy.py
4 年前
9835d26c
Prepare model for onnx export
4 年前
ca887743
Support tf and pytorch alongside one another
4 年前
1736559f
Combine actor and critic classes. Initial export.
4 年前
596cc103
Remove unused arg
4 年前
29223931
Fix for memories
4 年前
82688e5c
GRU in-progress and dynamic cnns
4 年前
212e2d1d
Merge remote-tracking branch 'origin/master' into develop-add-fire
4 年前
5f936990
Visual observations now train as well
4 年前
a5b5b109
Mulkti-discrete now working
4 年前
a11a79e4
Continuous and discrete now train
4 年前
4a50444f
Support discrete actions as well
4 年前
e6c9cbc6
Merge remote-tracking branch 'origin/develop-add-fire-debug' into develop-add-fire
4 年前
21a8de45
Fix normalization
4 年前
61d671d8
Add conditional sigma for distribution
4 年前
8c6f4696
Fix a couple additional bugs
4 年前
3c82bf59
Training runs, but doesn’t actually work
4 年前
947f0d32
Slightly closer to running model
4 年前
b997f214
Share more code between tf and torch policies
4 年前
2e51260a
Resolving a few bugs
4 年前
7c3bd376
Refactoring policy and optimizer
4 年前
6879bae4
Initial optimizer port
4 年前
e166d018
Dynamically construct actor and critic
4 年前
3769d943
Merge remote-tracking branch 'origin/master' into develop-add-fire
4 年前
c577ce26
Merge remote-tracking branch 'origin/master' into develop-add-fire
4 年前
dc50162d
Add ResNet and distributions
4 年前
3327c215
Begin porting work
4 年前
8b5587cc
Remove obsolete methods from Agent class ( #3770 )
* Removed the obsolete methods from the Agent class
* Documentation changes
* [skip ci] Update com.unity.ml-agents/CHANGELOG.md
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
* [skip ci] Update docs/Migrating.md
Co-Authored-By: Chris Elion <chris.elion@unity3d.com>
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
5 年前
dd6aa7e2
Agent.Heuristic takes an float[] ( #3765 )
5 年前
1843279a
[barracuda] Bump version to 0.6.3. ( #3766 )
5 年前
989cc89f
Use SemVer to check communication compatibility between C# and Python ( #3760 )
* [communication] Use semantic versioning to test communication compatibility between C# and Python.
- Add tests for the change.
Co-authored-by: Chris Elion <chris.elion@unity3d.com>
5 年前
893eb319
[MLA-858] Update the Editor Screenshot images ( #3759 )
* Removed the unused images from the images folder. Used the command
```
for f in *; do echo " file : $f" && grep -s -r "$f" /Users/vincentpierre/Documents/ml-agents -i --include *.md --exclude-dir=/Users/vincentpierre/Documents/ml-agents/docs/localized;done
```
to hunt the files down
* Modified the Unity Editor screenshots
* Addressing comments
5 年前
7e3848fe
[MLA-867] New integration tests for gym and llapi ( #3757 )
* [MLA-867] New integration tests for gym and llapi
* Fixing the command line argument in the test
* Fixing a bug that was blocking basic for ever
* Fixing typo
5 年前
05fc4c98
Update package_version timer metadata string ( #3761 )
5 年前
Ervin Teng
GitHub
Arthur Juliani