unity-tech-cn
/
ml-agents
46
14
派生 39
代码 合并请求 版本发布
2 提交
337 分支
128 Plastic标签
分支: develop/add-fire/continuous
分支列表 标签列表
${ item.name }
创建分支 ${ searchTerm }
从 'develop/add-fire/continuous'
${ noResults }

101 次代码提交 (develop/add-fire/continuous)

作者 SHA1 备注 提交日期
GitHub a28e2767 Update add-fire to latest master, including Policy refactor (#4263) 4 年前
GitHub 74c99ec8 [refactor] Refactor normalizers and encoders (#4275) 4 年前
GitHub 69579611 [refactor] Refactor Actor and Critic classes (#4287) 4 年前
Ruo-Ping Dong 6feec58a add Saver class (only TF working) 4 年前
Ervin Teng bd97532d Add normalizer update context 4 年前
GitHub 17f03980 [bug-fix] Fix non-LSTM SeparateActorCritic (#4306) 4 年前
GitHub d8db1477 [bug-fix] Fix error with discrete probs (#4309) 4 年前
Ruo-Ping Dong b98eb5f3 fix pytorch checkpointing. add tensors in Normalizer as parameter 4 年前
GitHub 5bcbef8d [tests] Add tests for core PyTorch files (#4292) 4 年前
Ruo-Ping Dong e7a4f325 remove print 4 年前
Andrew Cohen f74d301a Merge branch 'develop-add-fire' into develop-add-fire-bc 4 年前
Ruo-Ping Dong 6d67f857 move tf and add torch model serialization 4 年前
Andrew Cohen afe9861b add components directory and init 4 年前
Ervin Teng a172fb46 Halve entropy 4 年前
GitHub 38ce37c9 Add components directory and init (#4320) 4 年前
Andrew Cohen 6df8d32c Merge branch 'develop-add-fire' into develop-add-fire-bc 4 年前
Ruo-Ping Dong af2517a4 remove unused 4 年前
GitHub 69d29b86 [add-fire] Halve Gaussian entropy (#4319) 4 年前
Andrew Cohen 22a0cabc changed path to torch bc module 4 年前
GitHub 3a982317 [add-fire] Add learning rate and beta/epsilon decay to PyTorch (#4318) 4 年前
Andrew Cohen 8ced43ee clean up types/comments 4 年前
Ruo-Ping Dong bdb2ba93 small improvements 4 年前
GitHub 7ddfd81f Added Reward Providers for Torch (#4280) 4 年前
Andrew Cohen bf8b2328 Merge branch 'develop-add-fire' into develop-add-fire-bc 4 年前
GitHub dba529ff Fix discrete export (#4322) 4 年前
GitHub 36613cad [add-fire] Fix CategoricalDistInstance test and replace `range` with `arange` (#4327) 4 年前
Ervin Teng 6b29a4c9 Fix test and replace range with arange 4 年前
Ruo-Ping Dong 4e87b422 move checkpoint_path logic to saver 4 年前
GitHub 6b193d03 Develop add fire layers (#4321) 4 年前
Ervin Teng 6aa6c931 Added comment 4 年前
Ruo-Ping Dong 6fbd862e fix onnx input 4 年前
vincentpierre eb951ca0 fixing typo 4 年前
Ervin Teng cded4c6c Fix SeparateActorCritic and add test 4 年前
Ruo-Ping Dong 71fe4df6 fix formatting and test 4 年前
Ruo-Ping Dong b4713baa small improvements 4 年前
Ruo-Ping Dong 09a741c8 small improvement 4 年前
GitHub d1f60bef More comments and Made ResNetBlock (#4329) 4 年前
Ruo-Ping Dong 79d89158 Merge branch 'develop-add-fire' into develop-add-fire-checkpoint 4 年前
Ervin Teng 4ebccf97 Merge branch 'develop-add-fire' into develop-add-fire-sac-lst 4 年前
Andrew Cohen 598826fe Merge branch 'develop-add-fire' into develop-add-fire-bc 4 年前
Ruo-Ping Dong d3eb6c46 Merge branch 'develop-add-fire' into develop-add-fire-checkpoint 4 年前
GitHub 3b43972d Fixed the reporting of the discriminator loss (#4348) 4 年前
Andrew Cohen ae2c83e2 added torch bc tests 4 年前
Ruo-Ping Dong 95858e25 update saver interface and add tests 4 年前
GitHub 6b255790 Behavioral Cloning Pytorch (#4293) 4 年前
Andrew Cohen 742940a3 all bc tests 4 年前
GitHub f374f87a [add-fire] Add LSTM to SAC, LSTM fixes and initializations (#4324) 4 年前
Ervin Teng 1d4bc99e Proper mask mean for PPO 4 年前
Andrew Cohen 5f3a94cf address comments 4 年前
Ervin Teng 0ba67eb6 Fix ONNX import for continuous 4 年前
Ruo-Ping Dong f40996e2 fix export input names 4 年前
GitHub ce6ab357 Fix ONNX import for continuous 4 年前
Ruo-Ping Dong 0f148209 Merge branch 'develop-add-fire-checkpoint' of https://github.com/Unity-Technologies/ml-agents into develop-add-fire-checkpoint 4 年前
Ervin Teng eeae6d97 Proper initialization and SAC masking 4 年前
Andrew Cohen 0a7444f9 revert bc default batch/epoch 4 年前
Ruo-Ping Dong 6a3b38e1 fix export input name 4 年前
Ervin Teng 50b1470e Experimental amrl layer 4 年前
Ervin Teng 10be091f Redundant indexing 4 年前
Ruo-Ping Dong dbff06cd add comments 4 年前
Ervin Teng ef857c34 Add extra FF layer 4 年前
Ruo-Ping Dong 59cc1a9f Merge branch 'develop-add-fire' into develop-add-fire-checkpoint 4 年前
Ervin Teng b44b5a24 Faster implementation 4 年前
Ervin Teng ea7b85a7 Fix per-block lstm initialization 4 年前
Ervin Teng 11b30916 Add comment 4 年前
Ervin Teng f4da3592 Add memories and sequence length to critic_pass 4 年前
Ervin Teng 46f3a9b9 Passthrough max 4 年前
Ervin Teng d51cdf2e Fix memory logic in SeparateActorCritic 4 年前
Ervin Teng 13f15086 Merge branch 'develop-add-fire' into develop-add-fire-amrl 4 年前
Ervin Teng cb0085a7 Memory size abstraction and fixes 4 年前
Ervin Teng cb02ddbe Fix SeparateActorCritic 4 年前
Ervin Teng a88d3581 Fix and test for masked_mean 4 年前
Ervin Teng df6dc07a Fix SeparateActorCritic 4 年前
GitHub bd6bcd2f Merge master and add Saver class for save/load checkpoints 4 年前
Ervin Teng d22d2e26 LSTM class 4 年前
Ervin Teng d218bf4d Merge branch 'develop-add-fire' into develop-add-fire-sac-lst 4 年前
GitHub 6de31a03 [add-fire] Fix masked mean for 2d tensors (#4364) 4 年前
Ervin Teng 5c1717d1 Bugfixes for continuous case 4 年前
Ervin Teng 42e25b25 Merge branch 'develop-add-fire' into develop-add-fire-memoryclass 4 年前
Ervin Teng 9ae22c61 Fix SeparateActorCritic export 4 年前
Ervin Teng 28cea8c0 Add abstract method to Actor 4 年前
Ervin Teng 3387f56d Fix BC module 4 年前
GitHub 6a1d993f [add-fire] Memory class abstraction (#4375) 4 年前
Ervin Teng 019b3aa1 Remove some comments 4 年前
GitHub 2332bc32 Add fire to test_simple_rl.py (#4378) 4 年前
vincentpierre 349cee77 Fix of the test for multi visual input 4 年前
Ervin Teng 3a07f2bb Make reset block submodule 4 年前
Ervin Teng 1656d290 Clean up memory_size logic 4 年前
Ruo-Ping Dong cf1e7ca0 fix export input_name 4 年前
Ervin Teng d096f69c Fix layers reference 4 年前
Ervin Teng d63aacd0 Cleanup, add test 4 年前
Ruo-Ping Dong b8dbbc17 make visual input channel first for export 4 年前
Ervin Teng d21ffd02 Properly export memory size 4 年前
Ervin Teng 8ff8c401 Merge branch 'develop-add-fire' into develop-add-fire-export 4 年前
Ervin Teng d0e6d92f Fix exporting again 4 年前
Ervin Teng aeda0b32 Don't use torch.split in LSTM 4 年前
Ervin Teng ffbdc0e2 Merge branch 'develop-add-fire' of github.com:Unity-Technologies/ml-agents into develop-add-fire-export 4 年前
Ervin Teng da152b55 Fixed discrete models 4 年前
Ervin Teng 0b4a33d3 Always export one Action tensor 4 年前
GitHub a855cf09 Always export one Action tensor (#4388) 4 年前
Ruo-Ping Dong 964a2f76 add comment 4 年前
GitHub 347bde3d Fix export 4 年前