241 次代码提交 (97058b8b-0ed5-45e5-960f-f22df79428eb)

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
GitHub 17f03980 [bug-fix] Fix non-LSTM SeparateActorCritic (#4306) 4 年前
Ruo-Ping Dong bdb2ba93 small improvements 4 年前
Ruo-Ping Dong 4e87b422 move checkpoint_path logic to saver 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 79d89158 Merge branch 'develop-add-fire' into develop-add-fire-checkpoint 4 年前
GitHub f374f87a [add-fire] Add LSTM to SAC, LSTM fixes and initializations (#4324) 4 年前
Ervin Teng 0ba67eb6 Fix ONNX import for continuous 4 年前
Ervin Teng eeae6d97 Proper initialization and SAC masking 4 年前
Ervin Teng 50b1470e Experimental amrl layer 4 年前
Ervin Teng 10be091f Redundant indexing 4 年前
Ruo-Ping Dong 59cc1a9f Merge branch 'develop-add-fire' into develop-add-fire-checkpoint 4 年前
Ervin Teng f4da3592 Add memories and sequence length to critic_pass 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 df6dc07a Fix SeparateActorCritic 4 年前
Ervin Teng d22d2e26 LSTM class 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
GitHub 6a1d993f [add-fire] Memory class abstraction (#4375) 4 年前
Ervin Teng 019b3aa1 Remove some comments 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
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
GitHub 1955af9e [feature] Add experimental PyTorch support (#4335) 4 年前
Andrew Cohen 6587c911 hybrid bheavior spec 4 年前
Andrew Cohen 5b1620e9 moved encoders to processors 4 年前
Ervin Teng 1dca75d8 Move linear encoding to NetworkBody 4 年前
GitHub 9364048e Merge branch 'develop-pytorch-encoding' into develop-restructure-torch-networks 4 年前
Ruo-Ping Dong f5dee9d1 jit for continuous control 4 年前
Ruo-Ping Dong ef3be79e sac 4 年前
GitHub 4e93cb6e [torch] Restructure PyTorch encoders (#4421) 4 年前
GitHub beb5eb30 [bug-fix] Fixes for Torch SAC and tests (#4408) 4 年前
GitHub 6f534366 Add torch_utils class, auto-detect CUDA availability (#4403) 4 年前
GitHub 676f5f7c [refactor] Refactor GAIL to use new encoder structure (#4433) 4 年前
Andrew Cohen 3997b14b Merge branch 'master' into develop-hybrid-actions 4 年前
GitHub 069f10b9 [Bug fix] Export all branches for discrete control torch (#4491) 4 年前
Andrew Cohen 8294bc59 ignore commit 4 年前
GitHub fc557903 Develop fix visual torchh export (#4494) 4 年前
Ervin Teng 3e771cbb Permute visual obs outside of network 4 年前
Andrew Cohen b0b2e22e prepare to merge action_out 4 年前
Andrew Cohen 85602279 add action_out to dist 4 年前
Ervin Teng b6095151 Execute critic with LSTM 4 年前
vincentpierre 181bdec0 - 4 年前
Andrew Cohen 7c0aa77b Merge branch 'develop-actions-out' into develop-hybrid-actions 4 年前
Andrew Cohen b6b453a0 rename to exported model output 4 年前
Andrew Cohen 9cbf6c3f Merge branch 'develop-actions-out' into develop-hybrid-actions 4 年前
Andrew Cohen 72cd0d39 separate tensors for disc/cont 4 年前
Andrew Cohen 643c8e58 ppo extended 4 年前
Ervin Teng ba29b6b4 Change dimensions of recurrent in to BxN for ONNX 4 年前
Andrew Cohen db37db34 fixing errors 4 年前
Andrew Cohen 44c9879e action models 4 年前
Ervin Teng 8dec4771 Add hybrid actions to SAC 4 年前
Andrew Cohen 4b9a7db6 remove old behaviorspec 4 年前
GitHub e4db5dc5 ActionSpec and ActionBuffer (#4578) 4 年前
Andrew Cohen eaecb59e torch utils to and from buffer 4 年前
Andrew Cohen 8013e544 ignoring Instance of 'AbstractContextManager' has no 'enter_context' member (no-member) 4 年前
GitHub cb8e4d25 Add ActionSpec (#4586) 4 年前
Andrew Cohen b40e7793 fix mlagents-envs tests 4 年前
Andrew Cohen 9689cf2c remove *_action_* from function names 4 年前
Andrew Cohen dc89318d remove ActionType 4 年前
vincentpierre d3d4eb90 Trainer with attention 4 年前
vincentpierre 7ef3c9a1 Trainer with attention 4 年前
vincentpierre b09dfd0a Still not working 4 年前
GitHub 3c96a3a2 Action Model (#4580) 4 年前
vincentpierre c264b4da additional changes 4 年前
GitHub 88d3ec3e Merge master into hybrid actions staging branch (#4704) 4 年前
vincentpierre 9b3d4ade Fixing some issues 4 年前
GitHub 87a7ccf8 use int64 steps, check for NaN actions (#4607) 4 年前
GitHub 85a7c0f7 [bug-fix] Add clipping to PyTorch policy, fix initialization (#4649) 4 年前
vincentpierre 6fcbba53 Refactoring the code to make it more flexible. Still a hack 4 年前
vincentpierre 58f38662 Bigger network, needed to solve 4 年前
vincentpierre 0b6c2ed3 Fixing some bugs 4 年前
Andrew Cohen 84cc2b84 concat x self before attention 4 年前
vincentpierre e14e1c4d Improvements and new tests 4 年前
Andrew Cohen d62f6b0a modify bullet/attn 4 年前
Ervin Teng 78f88c15 Add clip to export and make optional in policy 4 年前
vincentpierre f283cb60 different architecture 4 年前
Ervin Teng 7a0ebfbd Pretty broken 4 年前
Ervin Teng 95bdbba3 Less broken PPO 4 年前
Ervin Teng 6c77ac7a Update SAC, fix PPO batching 4 年前
GitHub 94c59e31 C# changes for hybrid action spaces (#4587) 4 年前
Andrew Cohen bd917c9c action buffer passes continuous 4 年前
Ervin Teng 5a5bd515 Fix multiple obs 4 年前
Andrew Cohen ad951493 debugging discrete 4 年前
Andrew Cohen fcf6471e 2d discrete passes 4 年前
GitHub 990f801a Develop hybrid action staging (#4702) 4 年前
vincentpierre 735fcd52 [WIP] Refactor trainers to use list of obs rather than vec and vis obs 4 年前
Ervin Teng 6846af21 Multi-input network 4 年前
vincentpierre 93ca1409 fixing the tests 4 年前
Ervin Teng cb4b7ed3 Some minor tweaks but still broken 4 年前
vincentpierre 12619155 added some docstrings 4 年前
vincentpierre c1587bce Solving merge conflicts 4 年前
Ervin Teng 2b8ab09d Use Vince's ONNX export code 4 年前
Ervin Teng 558bfb70 Cleanup 4 年前
GitHub cc6b4564 Multi Directional Walker and Initial Hypernetwork (#4740) 4 年前
Ervin Teng 25dfd883 Merge branch 'master' into develop-centralizedcritic 4 年前
GitHub ad5f878c [refactor] Remove critic pass during inference (#4743) 4 年前
GitHub 22658a40 use sensor types to differentiate obs (#4749) 4 年前
vincentpierre 14378aa5 Merging master 4 年前
Ervin Teng ecac7ca1 Set num teammates to 2 4 年前
Arthur Juliani 95441b75 Use separate hypernetwork module 4 年前
GitHub 6f4f6044 Fix model inference issue with Barracuda v1.2.1 (#4766) (#4768) 4 年前
Ervin Teng 170c269e Remove prints 4 年前
Andrew Cohen 498b1ee6 Merge branch 'develop-action-buffer' into develop-hybrid-actions-singleton 4 年前
Andrew Cohen 06f1f254 1:1 and continuous/discrete train 4 年前
Ervin Teng 2462db69 Add comment to ghost trainer 4 年前
vincentpierre c3699de8 merging master and addressing comments 4 年前
vincentpierre e0cf88e6 Made a nicer comment 4 年前
Ervin Teng e4e0e2bd Scale size of CC network 4 年前
Andrew Cohen 1d234d1d bc works 4 年前
vincentpierre 719c969c addressing comments. ObservationSpec is no longer a list 4 年前
Ervin Teng a3885120 Scale value network based on num agents 4 年前
vincentpierre 4bba4e8e Renaming ObservationSpec to SensorSpec 4 年前
Andrew Cohen e81e68de comms agent and fixed hallway 4 年前
vincentpierre 44ed3258 Merging master 4 年前
vincentpierre 449712b0 renaming sensor_spec to sensor_specS 4 年前
Andrew Cohen 17496265 move AgentAction, ActionLogProbs, and ActionFlattener to separate files 4 年前
vincentpierre f7a4a31f [Experiment] Bullet hell 4 年前
Andrew Cohen f57875e0 layer norm 4 年前
Andrew Cohen bc77c990 layer norm and weight decay with fixed architecture 4 年前
Ervin Teng 330fc1d0 Merge branch 'master' into develop-centralizedcritic-mm 4 年前
Andrew Cohen fad37dc5 add default args to LinearEncoder 4 年前
Ervin Teng ad439fb6 Additional changes 4 年前
Andrew Cohen 21365c04 formatting 4 年前
Ervin Teng d02a1033 Some more fixes 4 年前
Andrew Cohen 96c01a63 custom layer norm 4 年前
Ervin Teng efa67290 Self-attention Centralized Critic 4 年前
GitHub d7c3022d Export separate nodes for continuous/discrete actions (#4655) 4 年前
Andrew Cohen 90e0e8b2 concat self 4 年前
HH 5c5539af add zomb scene 4 年前
Andrew Cohen 89ed777e increase bullets to 40 4 年前
Andrew Cohen 231328ea remove warning prints 4 年前
Arthur Juliani 0b4b0992 Rename more files 4 年前
Arthur Juliani 7c37c759 Fix some mis-renamings 4 年前
vincentpierre 56972f56 WIP integrate attention to networkbody 4 年前
Ervin Teng aba633b2 Merge branch 'develop-attention-refactor' into develop-centralizedcritic-mm 4 年前
vincentpierre d27459bd Fix error in embedding 4 年前
Ervin Teng 135914fd entity embeddings work with no max 4 年前
vincentpierre af58753b adding encoding to self and var len input 4 年前
Ervin Teng 9a3598eb Use 4 heads 4 年前
vincentpierre e7024786 Removing hacky layer norm 4 年前
Arthur Juliani e3de0406 Plurals 4 年前
Andrew Cohen b0c02ee0 Merge branch 'develop-hybrid-actions-csharp' into develop-actionmodel-csharp 4 年前
Ervin Teng 9c3da1b6 New buffer layout, TeamObsUtil, pad dead agents 4 年前
vincentpierre 8660b1c2 merging master 4 年前
Ervin Teng eab7e42a Use NaNs to get masks for attention 4 年前
Ervin Teng bf7195f1 Refactor multi input network slightly 4 年前
Ervin Teng 1c557bd3 Don't concat self 4 年前
vincentpierre 38fc2536 addresing some comments 4 年前
Ervin Teng 6b8b3db3 Try subtract marginalized value 4 年前
GitHub e9ff7705 Fix torch tensor non-contiguous issue (#4855) 4 年前
Andrew Cohen ad807327 refactor entityembedding/network body 4 年前
GitHub 01e0ee00 refactor entityembedding/network body (#4857) 4 年前
Ervin Teng 5d7345a6 Add Q function with attention 4 年前
Andrew Cohen 6e6f3246 clean up 4 年前
Ervin Teng 092ea232 Some more progress - still broken 4 年前
Andrew Cohen 4e37974c moved embedding layer norm into network body 4 年前
GitHub 89b6c949 use singular entity embedding (#4873) 4 年前
Ervin Teng 457b2630 I think it's running 4 年前
Andrew Cohen 5caaef52 move entity max computation to network body 4 年前
Andrew Cohen 44088167 separate forward into q_net and baseline 4 年前
Andrew Cohen 6e1826f8 might be right 4 年前
vincentpierre 52b011d6 _ 4 年前
Andrew Cohen 1511588d forcing this to work 4 年前
vincentpierre 396bc43c Merging master 4 年前
vincentpierre b7c7d773 Adding some tests 4 年前
vincentpierre 6f3ea7b8 _ 4 年前
vincentpierre 92005ea6 Better placeholder for encoded_self than None 4 年前
Andrew Cohen feb38012 add lambda return and target network 4 年前
Arthur Juliani e8d54b6f Use hypernetwork if there is a goal 4 年前
Arthur Juliani 512482c8 Check that goal is a goal 4 年前
Arthur Juliani 1cf97635 Additional conditional experiments 4 年前
vincentpierre 7e47f94b addressing comments 4 年前
Andrew Cohen a4c336c2 value estimator 4 年前
Arthur Juliani d2526ce2 Modify CrawlerDynamic 4 年前
vincentpierre c27a95f0 Make a self encoder before EntityEmbedding 4 年前
vincentpierre 2bf6737f addressing comments 4 年前
Arthur Juliani b8e81b00 Make lists modulelists 4 年前
vincentpierre fd007f53 Attempting to use EntityEmbedding directly as processor 4 年前
vincentpierre efa5a164 addressing comments and adding the changes to rpc_utils 4 年前
vincentpierre 19a8244b [skip ci] Removing no-longer-useful comment 4 年前
Arthur Juliani 21aaa5fe Add goal to hyper input 4 年前
Arthur Juliani a180dbf7 Add visual version of task and simply encoders 4 年前
Andrew Cohen 7f491ae7 cloud run with coma2 of held out zombie test env 4 年前
vincentpierre 9fbc2e0e _ 4 年前
Arthur Juliani 7165e9cf Make conditiontype a setting 4 年前
Andrew Cohen 9af22d30 use only value funcs 4 年前
vincentpierre bf16bad6 _ 4 年前
Andrew Cohen 511a9a7e no baseline 4 年前
vincentpierre 6a61eb05 - 4 年前
vincentpierre 1acdc155 Changes to hypernet 4 年前
vincentpierre 82d80d72 better error message 4 年前
Andrew Cohen 687f411b try again on cloud 4 年前
Arthur Juliani 1d106816 Support multiple goals in networkbody 4 年前
Arthur Juliani 7ba4ca17 Reformat line 4 年前
Arthur Juliani 2552cf18 Address comments 4 年前
Andrew Cohen f9ff3fef shared baseline and v 4 年前
Ervin Teng bca6c92c Add clipping, use same network for value 4 年前
Ervin Teng 3283b6a1 Remove Q-net for perf 4 年前
Ervin Teng 2be83146 Use same network 4 年前
Ervin Teng 6094613d try reduce bias more 4 年前
Andrew Cohen c08fefbc reduce initialization weights 4 年前
Ervin Teng b6f88d6d Merge branch 'develop-base-teammanager' into develop-agentprocessor-teammanager 4 年前
Andrew Cohen eeabb974 Separate Actor/Critic, remove ActorCritics 4 年前
Ervin Teng 7c826fb1 Working GRU 4 年前
Ervin Teng 514873bf Use correct memories (t-1 instead of t) for training 4 年前
Ervin Teng e9025079 Properly use MemoryModule abstraction 4 年前
Andrew Cohen c74dca9f add SharedActorCritic 4 年前
Ervin Teng f3a2a81f Merge branch 'develop-fix-lstms' into develop-gru 4 年前
Andrew Cohen 98d647de MultiInputNetBody 4 年前
Ervin Teng e46a86ad Merge branch 'master' into develop-superpush-int 4 年前
Ervin Teng 9bc88c41 Running COMA (not sure if learning) 4 年前
vincentpierre 22db0335 Modified the model_serialization to have correct inputs and outputs 4 年前
Andrew Cohen 5d517c5e clean ups 4 年前
Andrew Cohen 8562471e add inital coma optimizer tests 4 年前
GitHub c9c7e3d0 Faster NaN masking, fix masking for visual obs (#5015) 4 年前
Arthur Juliani f49dcf8e Update network (partially) 4 年前
Ervin Teng fd0dd35c Merge branch 'main' into develop-coma2-trainer 4 年前
Arthur Juliani ce1d3d88 Resolve conflicts in networkbody 4 年前
Arthur Juliani fc1ee931 Fix hypernetwork 4 年前
GitHub 0ddfbfee V2 staging new model version (#5080) 4 年前
GitHub f16ce486 Update v2-staging from main (March 15) (#5123) 4 年前
GitHub 6ae8ea1e [coma2] Add support for variable length obs in COMA2 (#5038) 4 年前
GitHub 8f35bdd3 POCA trainer (#5005) 4 年前
GitHub e79d8a9d [bug-fix] Move POCA critic to default device (#5124) 4 年前
Christopher Goy 90872d1d V2 staging new model version (#5080) 4 年前
vincentpierre e83c350a Fixing networks.py for the merge 4 年前
GitHub 81705d6d Goal conditioning integration (#5142) 4 年前
GitHub c37cfac1 Adding the goal conditioning sensors with the new observation specs (#5159) 4 年前
GitHub dffc37bf Update to barracuda 1.3.3 and changes to the model inputs and outputs for LSTM (#5236) 4 年前
vincentpierre 51adab1c Fix the attention module embedding size 4 年前
GitHub 1678be1c POCA Attention will use h_size for embedding size and not 128 (#5281) 4 年前