373 次代码提交 (a73f7d73-79e8-4953-a855-49e9c25fd1f8)

作者 SHA1 备注 提交日期
GitHub d816c37c pin pip to 20.2 for now (#4694) 4 年前
GitHub 9cc20101 Fix heuristic example and some crefs (#4690) 4 年前
GitHub c11e939b Add link to curriculum docs in learning environment design (#4687) 4 年前
GitHub b464678d Merge pull request #4682 from Unity-Technologies/r10-to-master 4 年前
GitHub edc2ae2f [bug-fix] Disable threading for self-play envs (#4679) 4 年前
GitHub 4617a7b6 [bug-fix] Remove extra period (#4674) 4 年前
GitHub 1cac78e2 [Bug-fix] Remove extra directory created at checkpoint (#4675) 4 年前
GitHub de27d7a6 [bug-fix] Fix issue where NaNs are outputted by the policy when training Match3 (#4664) 4 年前
GitHub 8175d558 [bug-fix] Fix BC module + action clipping (#4667) 4 年前
GitHub efdb1042 Add global lock for torch.onnx.export() (#4659) 4 年前
GitHub 3ab45b3f [bug-fix] Separate critic only for PPO (#4661) 4 年前
GitHub 078de517 🇺🇸 fix spelling 🇺🇸 (#4663) 4 年前
GitHub 85a7c0f7 [bug-fix] Add clipping to PyTorch policy, fix initialization (#4649) 4 年前
Ruo-Ping Dong 1ab8871e check tensor exist before access shape 4 年前
Ruo-Ping Dong 8ed14762 Merge branch 'develop-hybrid-actions-singleton' into develop-hybrid-actions-csharp 4 年前
Ervin Teng 5ee6efb0 Make collab env harder 4 年前
Chris Elion 8cf87ed6 match3 settings 4 年前
Ervin Teng e05e0aef Collaborative walljump 4 年前
GitHub 87a7ccf8 use int64 steps, check for NaN actions (#4607) 4 年前
GitHub 4dd42642 Bumping versions on master for release_10 (#4642) 4 年前
GitHub 7cdf3efe Update CONTRIBUTING.md (#4602) 4 年前
GitHub 8a1f0a8b Updating the CHANGELOG on master before release 10 (#4636) 4 年前
GitHub d490bb44 add match3 to changelog (#4635) 4 年前
GitHub 1b933a0a Add Graphics to the Match3 env (#4627) 4 年前
GitHub 90a9d214 Match3 example (#4515) 4 年前
GitHub fb4661b0 Merge release_9_branch to master (#4623) 4 年前
vincentpierre 96452986 Initial commit for multi head attention 4 年前
GitHub 95efe03b [MLA-1519] Don't mark action_probs as an output node. (#4613) 4 年前
GitHub 64e998a2 [bug-fix] Use float64 when converting np.ndarray to torch.tensor, cap Torch version to 1.7.x (#4610) 4 年前
GitHub 6ce2434d Fix typo in URL (#4604) 4 年前
GitHub a4ba90ec [bug-fix] Fix ONNX export/Barracuda import for continuous actions (#4608) 4 年前
GitHub cb8e4d25 Add ActionSpec (#4586) 4 年前
GitHub 0e91ff08 Reword readme (#4603) 4 年前
GitHub 8669e389 Refactor BarracudaModel loader checks (#4629) 4 年前
GitHub e0ef30a5 [bug-fix] Change entropy computation and loss reporting in Torch to match TF (#4538) 4 年前
GitHub 5e5ff19b Barracuda inference for hybrid actions (#4611) 4 年前
GitHub b5dd43f2 [bug-fix] Don't load non-wrapped policy (#4593) 4 年前
GitHub d91d4a19 ActionBuffer with hybrid actions for RemotePolicy (#4592) 4 年前
GitHub a7f10f8a Update Training-on-Amazon-Web-Service.md (#4591) 4 年前
GitHub ca1aacc1 Assign new BrainParametersProto fields based on capabilities (#4581) 4 年前
GitHub a690af74 [refactor] Make PyTorch the default and TensorFlow optional (#4517) 4 年前
GitHub be723c66 Change BrainParametersProto to support ActionSpec (#4579) 4 年前
GitHub 7a33b67a update barracuda version, enable tests for 2020.2 (#4571) 4 年前
GitHub 4cfae52e Add hybrid action capability flag (#4576) 4 年前
GitHub dde34423 [bug-fix] Use proper masking for entropy and policy losses (#4572) 4 年前
Ruo-Ping Dong 91700916 add hybrid action capability flag 4 年前
GitHub 024bb104 [MLA-1474] detect recursion on Agent methods and throw (#4573) 4 年前
GitHub dc40c926 Merge release 8 back to master (#4570) 4 年前
GitHub 82debf3b clean up EndEpisode demo code (#4563) 4 年前
GitHub 86d8ee4a use v2 action and pin python version (#4568) 4 年前