2552 次代码提交 (86ff4c4a-2257-4271-9eb7-6299f25e3091)

作者 SHA1 备注 提交日期
Deric Pang 479f7046 Addressing Arthur's PR comments. 6 年前
Deric Pang d4ca94a1 Merge remote-tracking branch 'upstream/develop' into develop-flat-code-restructure 6 年前
Deric Pang 20dd50c4 Addressing feedback from offline meeting. 6 年前
Deric Pang b5561409 Updating install_requires to be more strict. 6 年前
GitHub 3900ed66 Merge pull request #1083 from Unity-Technologies/develop-flat-code-restructure 6 年前
Deric Pang b7cd57db Printing Unity logo exception is now caught. 6 年前
Deric Pang 55257ee7 Changing the way Unity Technologies is printed by default. 6 年前
GitHub edfedbdb Enforce the grpcio version more strictly, should consider enforcing other packages versions as well (#1132) 6 年前
GitHub e9e582c9 Merge pull request #1128 from Unity-Technologies/develop-fix-print-logo 6 年前
GitHub a776c668 Added a README for the ml-agents package (#1136) 6 年前
GitHub b7e63bd8 Fix seed with multiple runs (#1138) 6 年前
GitHub c8371e3b Print summaries at inference (#1143) 6 年前
GitHub fbf92810 Refactor Trainers to use Policy (#1098) 6 年前
Arthur Juliani bb135f4f Python version is now restricted to 3.5 or 3.6. (#1145) 6 年前
GitHub 10d2a19d Release v0.5 (Develop) (#1203) 6 年前
GitHub f8df71a0 Revert "Release v0.5 (Develop) (#1203)" (#1222) 6 年前
GitHub ab5c49e8 Release v0.5 delete unityagents (#1151) 6 年前
GitHub 6430fc86 Changing learn.py log messages. (#1159) 6 年前
GitHub 2d4b4209 Use single scope declaration for models (#1160) 6 年前
GitHub a6f45b76 Fixing learn.py, trainer_controller.py, and Docker (#1164) 6 年前
GitHub ffffe131 Renamed MLAgentsSDK to UnitySDK. (#1170) 6 年前
GitHub 29084e77 Curriculum learning reward thresholding bug fix (#1141) 6 年前
Arthur Juliani 2cd8e250 Documentation 0.5 Release Check List (Part 1) (#1154) 6 年前
GitHub 6b04b516 Consistent string style in trainer_controller.py (#1177) 6 年前
GitHub ab6eb8dc Fix TF Nan bug (#1178) 6 年前
GitHub a54714f8 Update API to version 5 (#1179) 6 年前
GitHub 2af80543 Add fix for multiple instances on a single GPU (#1192) 6 年前
GitHub 4a881354 fix the training doc (#1193) 6 年前
GitHub af7de3ca Fix bug when academy max steps is set to nonzero value. (#1195) 6 年前
GitHub a884806b Update readmes to be more informative (#1194) 6 年前
GitHub 020d6e8b Fixing tables in documentation and other markdown errors. (#1199) 6 年前
GitHub 25495874 Merge pull request #1223 from Unity-Technologies/release-v0.5 6 年前
GitHub 560f1bd7 Merge pull request #1224 from Unity-Technologies/release-v0.5 6 年前
GitHub d2c320dd Remove graph scope (#1205) 6 年前
GitHub cf71145c removed the logging.basicConfig in other files, so that we have one place to control this (#1285) 6 年前
GitHub 3c9603d6 Demonstration Recorder (#1240) 6 年前
GitHub d7224351 Brains as Scriptable Objects (#1250) 6 年前
GitHub 840417ff Use organized tags for tensorboard stats (#1248) 6 年前
GitHub 6c354d16 New Learning Brain (#1303) 6 年前
GitHub c4fa3893 Add file check & reuse protobuf conversion functions (#1316) 6 年前
GitHub 2b6b4570 Fix the Python Tests (#1327) 6 年前
vincentpierre 03a8b7ed fix discrete curiosity 6 年前
vincentpierre 1045b6e7 Fix continuous curriosity 6 年前
GitHub 78374601 vince's fix for model step (#1329) 6 年前
GitHub 547f0e98 Merge pull request #1361 from Unity-Technologies/release-v0.6 6 年前
GitHub 48578199 Fix brain name bug in offline bc (#1395) 6 年前
GitHub 2d68b835 Check that worker port is available in RpcCommunicator (#1415) 6 年前
Arthur Juliani 4dce8f6a Sleep three seconds between session launches 6 年前
eshvk 4a96b14d Fixes to container workflow for GCP 6 年前
Arthur Juliani fa3bee21 Use queue to check for environment launch 6 年前
eshvk 3755a211 Refactor and clean up code 6 年前
vincentpierre eb4e23a7 making masked actions impossible instead of improbable 6 年前
Arthur Juliani e07bfab2 Address comments 6 年前
GitHub 2d126438 Merge pull request #1459 from Unity-Technologies/develop-docker-fix 6 年前
GitHub 5b68086c Merge pull request #1427 from Unity-Technologies/coldfix-action-masking 6 年前
Jonathan Harper 2127d15a Limit pytest <4.0.0 6 年前
Jonathan Harper 28041df6 Remove requirements.txt 6 年前
vincentpierre 47de43f6 reverted .tf to .bytes into the policy.py script 6 年前
GitHub e9121bb5 Merge pull request #1451 from Unity-Technologies/release-v0.6-revertTF1 6 年前
vincentpierre 4225c4e0 Bug fix for the pytests of the worker-id 6 年前
vincentpierre a9b5ad37 Ticked the communication version to API-6 6 年前
GitHub c1711546 Merge pull request #1468 from Unity-Technologies/release-v0.6-tick-communication 6 年前
vincentpierre f1e4883a Added a test 6 年前
vincentpierre 886e1c9b Ticked the version in the tests 6 年前
vincentpierre 4c9db846 added a docstring 6 年前
GitHub 2b9fce51 Merge pull request #1469 from Unity-Technologies/release-v0.6-tick-version-test-fix 6 年前
GitHub 450e8bfa Merge pull request #1466 from Unity-Technologies/release-v0.6-bug-fix-worker-id 6 年前
Jonathan Harper 35f06d90 Patch communicator in test to prevent port reservation 6 年前
vincentpierre 99aaa15e made the pytest directory agnostic 6 年前
GitHub b946047a Merge pull request #1470 from Unity-Technologies/release-v0.6-make-test-directory-agnostic 6 年前
GitHub a60e1853 Merge pull request #1419 from Unity-Technologies/develop-multi-delay 6 年前
vincentpierre c89ac855 tick the version number 6 年前
Arthur Juliani fc39442b Move done and reward to buffer from demonstration 6 年前
vincentpierre d1cb6ce0 Fix on the bc_offline_training using deep copies 6 年前
GitHub 13d38179 Merge pull request #1490 from Unity-Technologies/release-v0.6-fix-bc-offline 6 年前
GitHub 87a30e34 Support both 32-bit and 64-bit types in UnityEnvironment (#1471) 6 年前
GitHub facf2c5c Merge pull request #1491 from Unity-Technologies/fix-demo-buffer 6 年前
GitHub e73686c4 Merge pull request #1489 from Unity-Technologies/release-v0.6-tick-version 6 年前
GitHub f5764c98 Merge branch 'develop' into release-v0.6 6 年前
GitHub c8cc5a29 Merge pull request #1495 from Unity-Technologies/release-v0.6 6 年前
GitHub a196dde2 Merge pull request #1494 from Unity-Technologies/release-v0.6 6 年前
GitHub b6c97cb6 Fix for divide-by-zero error with Discrete Actions (#1520) 6 年前
GitHub cc083fd8 fixed the windows ctrl-c bug (#1558) 6 年前
GitHub 3523f9be Only using multiprocess when --num-runs>1 (#1583) 6 年前
GitHub 9708d865 Fix In editor Docker training (#1582) 6 年前
GitHub 8b1f0a38 Merge pull request #1589 from Unity-Technologies/hotfix-0.6.0a 6 年前
GitHub c0c289cc Merge pull request #1588 from Unity-Technologies/hotfix-0.6.0a 6 年前
GitHub 517e3a0a Remove env creation logic from TrainerController (#1562) 6 年前
Vincent-Pierre BERGES 4a6ae4e0 Barracuda integration into ML-Agents (#1557) 6 年前
GitHub cd087609 added the pypiwin32 package (#1668) 6 年前
GitHub 249e86a4 Ticked API : (#1696) 6 年前
GitHub 4846907e Add timeout wait param (Develop) (#1700) 6 年前
Jonathan Harper 35eb595d Add back 'get_communicator' in UnityEnvironment 6 年前
GitHub c258b1c3 Move 'take_action' into Policy class (#1669) 6 年前
GitHub a84dccab Update Timeout error messages (#1750) 6 年前
GitHub cfb8f208 Release v0.7 minor fixes (#1759) 6 年前
GitHub 275ff5d6 Merge pull request #1764 from Unity-Technologies/release-v0.7 6 年前
GitHub 20ff1436 Merge pull request #1765 from Unity-Technologies/release-v0.7 6 年前
Vincent-Pierre BERGES bc636075 API for sending custom protobuf messages to and from Unity. (#1595) 6 年前
Ervin T b30f4c90 Split `mlagents` into two packages (#1812) 6 年前
eshvk cc9bdf17 Added logging per Brain of time to update policy, time elapsed during training, time to collect experiences, buffer length, average return 6 年前
eshvk fb04c40c Reorganize to make metrics collection more accurate 6 年前
GitHub a0b44f1b Merge pull request #1858 from Unity-Technologies/develop-esh-metrics 6 年前
GitHub 93760bc4 Adds SubprocessUnityEnvironment for parallel envs (#1751) 6 年前
eshvk a50aadda * Ticked API : 6 年前
Jonathan Harper 7a0d1531 Fix subprocess model saving on Windows 6 年前
Jonathan Harper e91e847c Fix '--slow' flag after environment updates 6 年前
GitHub c613df3a Merge pull request #1922 from Unity-Technologies/release-v08-slowflag 6 年前
GitHub 2d1bda57 Merge pull request #1931 from Unity-Technologies/release-v0.8 6 年前
GitHub ba57eaad Merge pull request #1932 from Unity-Technologies/release-v0.8 6 年前
eshvk fc6d729f Explicitly adding all packages as imports 6 年前
eshvk eda78c63 Release 0.8.1 to fix pypi issues 6 年前
GitHub 588c8f8d Merge pull request #1942 from Unity-Technologies/hotfix-pypi 6 年前
GitHub 3dd69856 Merge pull request #1941 from Unity-Technologies/hotfix-pypi 6 年前
eshvk ef8009d9 Python code reformat via [`black`](https://github.com/ambv/black). 6 年前
GitHub 70d14910 Merge pull request #1934 from Unity-Technologies/develop-black 6 年前
Mantas Puida 27567062 First stage of ML Agents update to Barracuda 0.2.x 6 年前
Mantas Puida 8a5d17da Upgraded to Barracuda 0.2.1, fixes issues with discrete action models 6 年前
Mantas Puida 5566f8a8 Added Barracuda 0.2.2 6 年前
Jonathan Harper d9a7e5b6 Fix failure on Academy Done() with parallel envs 6 年前
GitHub f13d0f11 Merge pull request #2049 from Unity-Technologies/develop-barracuda-0.2.0 6 年前
Vincent(Yuan) Gao a15763f8 Clear cumulative_returns_since_policy_update (#2120) 6 年前
GitHub a4d5b2d3 Doc/comment cleanup - Fix some occurrences of 'the the' (#2119) 6 年前
Ervin T a3d03fb4 run black on ml-agents (#2125) 6 年前
GitHub e916dc48 use yaml.safe_load instead of yaml.load (#2124) 6 年前
Yuan Gao fa4d61b5 Bumping the ml-agents, ml-agents-envs, gym_unity versions 6 年前
GitHub 4966b888 Fixed the import issue (#2158) 6 年前
GitHub d5f6b7f8 Merge pull request #2157 from Unity-Technologies/release-v0.8.2 6 年前
GitHub dcef9f69 Merge pull request #2179 from Unity-Technologies/release-v0.8.2 6 年前
GitHub 2671e1a0 Enable mypy in precommit checks (#2177) 6 年前
GitHub 40c7fc48 Merge branch 'develop' into protobuf_update 6 年前
GitHub 4ac79742 Refactor reward signals into separate class (#2144) 5 年前
Jonathan Harper 177ee5b8 Remove unused "last reward" logic, TF nodes 5 年前
GitHub b05c9ac1 Add environment manager for parallel environments (#2209) 5 年前
Chris Elion bb7773c1 add flake8 to precommit 5 年前
GitHub 966d8efb Remove "external_brains" arg for TrainerController (#2213) 5 年前
Chris Elion af4699ac Fix reference to external_brains in TrainerController (#2237) 5 年前
Chris Elion 2f9c3ed5 enforce line length 5 年前
Chris Elion e69ddc53 cleanup setup.cfg 5 年前
GitHub 84d9d622 python timers (#2180) 5 年前
Chris Elion 85809f78 remove unused variables 5 年前
GitHub d80d5852 add some types to the reward signals (#2215) 5 年前
GitHub 9c50abcf GAIL and Pretraining (#2118) 5 年前
GitHub 1c18bd18 Swap 0 set and reward buffer append (#2273) 5 年前
GitHub a5b7cf95 Fix get_value_estimate and buffer append (#2276) 5 年前
Chris Elion 5d07ca1f Merge remote-tracking branch 'origin/develop' into enable-flake8 5 年前
Chris Elion dfdf7b83 fix whitespace and line breaks 5 年前
Chris Elion c58c2600 remove unused variables 5 年前
Chris Elion 9924c40e one more unused 5 年前
GitHub f8041534 Merge pull request #2236 from Unity-Technologies/enable-flake8 5 年前
GitHub be4292fb Add different types of visual encoder (nature cnn/resnet) 5 年前
GitHub 19283bfa Very simple environment for testing (#2266) 5 年前
GitHub 6a212f73 Improvements for GAIL (#2296) 5 年前
GitHub 9eb3f049 Cleanup unused code in TrainerController (#2315) 5 年前
GitHub 6225317d refactor vis_encoder_type and add to doc 5 年前
Ervin T a46f3faa Enable generalization training (#2232) 5 年前
GitHub 83875376 Add "gauges" to timer system (#2329) 5 年前
GitHub 33cb438b Tick version number for 0.9 (#2331) 5 年前
GitHub 4991d83f Merge pull request #2346 from Unity-Technologies/release-0.9.0 5 年前
Ervin T 7cfce1a9 Barracuda hotfix for LSTM and tests (#2352) 5 年前
GitHub 9178b5d2 Improve test_simple.py and check discrete actions (#2345) 5 年前
GitHub dd0d2a10 Remove unnecessary feed_dicts for GAIL and Curiosity (#2348) 5 年前
GitHub 78c0c202 fix mock_brain (#2377) 5 年前
Jeffrey Shih 728afebf Release 0.9.0 docs checklist and cleanup - v2 (#2372) 5 年前
Jonathan Harper 98297be9 Fix training not quitting when play button is unchecked (#2376) 5 年前
GitHub 53475207 Merge pull request #2380 from Unity-Technologies/release-0.9.0 5 年前
GitHub c7f0ed04 Merge pull request #2381 from Unity-Technologies/release-0.9.0 5 年前
GitHub b498c19d Fix BCTrainer increment_steps (#2384) 5 年前
GitHub a9fe719c Add Multi-GPU implementation for PPO (#2288) 5 年前
Ervin Teng 77849adf Increment package ver. Only trainers were changed. 5 年前
GitHub d7ebaae1 Return list instead of np array for make_mini_batch() (#2371) 5 年前
GitHub 30930383 Move trainer initialization into a utility function (#2412) 5 年前
Ervin T 184b5d5a Change samplers to use random state to allow consistency in reset par… (#2398) 5 年前
sankalp04 121221f2 Adding new command line arguments 5 年前
GitHub 7b69bd14 Refactor Trainer and Model (#2360) 5 年前
GitHub ab690b93 Fix naming conflict between Curiosity and GAIL (#2406) 5 年前
sankalp04 dfc8885d Allow generalization training with specified arguments of min_reward and min_lesson_length 5 年前
Ervin Teng 866212b1 Tick version to 0.9.0a 5 年前
sankalp04 c9ea139f Change reset parameters based on reward or progress metric 5 年前
GitHub afb6ede5 Merge pull request #2393 from Unity-Technologies/hotfix-v0.9.0a 5 年前
sankalp04 0b006719 Incorporate generalization checks for resetting parameters in take_step 5 年前
Ervin Teng a78ea129 Re-tick version for pypi 5 年前
GitHub c2bde29b Merge pull request #2420 from Unity-Technologies/hotfix-v0.9.1 5 年前
Ervin Teng 072d2ef8 Merge latest develop 5 年前
sankalp04 74245e35 Add LessonControllerError to track errors in LessonController 5 年前
Ervin Teng c912d140 Make sure all tests pass on BC 5 年前
sankalp04 8cbfee43 Get rid of dead code and clean up code 5 年前
GitHub 4472838e Merge pull request #2421 from Unity-Technologies/hotfix-v0.9.1 5 年前
sankalp04 dacb420b Instantiate SamplerManager in learn.py instead of trainer_controller 5 年前
GitHub bd7eb286 Update reward signals in parallel with policy (#2362) 5 年前
sankalp04 db858686 Made the code cleanup changes - mostly nit changes 5 年前
sankalp04 f331e5b7 Rebase develop 5 年前
GitHub 689765d6 Modification of reward signals and rl_trainer for SAC (#2433) 5 年前
GitHub 43696d60 Fix bug in add_rewards_output and add test (#2442) 5 年前
GitHub 3880fd3a Update development release version to 0.10.0.dev0 (#2443) 5 年前
Yuan Gao f33830bc Updated the python packages version to 0.9.2 5 年前
GitHub 0afd58fc More flexibility on the h5py version 5 年前
GitHub be66102d Merge pull request #2471 from Unity-Technologies/setup.py-h5py-version 5 年前
Yuan Gao b9210f4c Updated the comment for —multi-gpu option. 5 年前
GitHub df0196f9 Merge pull request #2472 from Unity-Technologies/release-0.9.2-multi-gpu-doc 5 年前
Yuan Gao 33404e1b Fixed the flake8 5 年前
GitHub c13828ce Merge pull request #2474 from Unity-Technologies/release-0.9.2-flake8-fix 5 年前
GitHub 0a163871 Merge pull request #2469 from Unity-Technologies/release-0.9.2 5 年前
GitHub cf9e67fb Merge pull request #2470 from Unity-Technologies/release-0.9.2 5 年前
GitHub e2e31cbb new versions (#2504) 5 年前
GitHub f628d18b initialize trainer step count (#2498) (#2505) 5 年前
GitHub b73fa378 Add more extensive tests for BC trainer (#2506) 5 年前
GitHub bf375235 Change update buffer to float32 instead of float64 (#2461) 5 年前
GitHub dc3ab81a Merge pull request #2514 from Unity-Technologies/hotfix-0.9.3 5 年前
Ervin Teng e0da93d1 Fix bug with construct_curr_info and test 5 年前
Ervin Teng aca81efb Add more tests 5 年前
Ervin Teng 28ef8983 Add 2 visual obs test 5 年前
GitHub 4bb97e25 Fix bug with construct_curr_info (#2490) 5 年前
GitHub 25926795 initialize trainer step count (#2498) 5 年前
GitHub 6a81a2f4 Add Soft Actor-Critic as trainer option (#2341) 5 年前
Jonathan Harper 2f083c8a Renamed "StepInfo" to "EnvironmentStep" 5 年前
GitHub 7ec3d7ad Merge pull request #2516 from Unity-Technologies/master 5 年前
GitHub 6f67cf40 unit test - don't use global random generator (#2521) 5 年前
GitHub 876aca1e Use numpy for random sample in buffer (#2524) 5 年前
GitHub 9e2c30ee Made the _check_environment_trains test a little more easy to pass so the test will not randomly fail (#2520) 5 年前
GitHub 0390c78b Fix determinism in unit test (#2530) 5 年前
GitHub 7720db33 Fix run_id typing in trainer.py (#2537) 5 年前
GitHub 3df585d9 Fix issue where SAC encoder type is always simple (#2548) 5 年前
Ervin Teng 4cb340b5 Fix crash when next_info is empty and using recurrent 5 年前
Ervin Teng 38b872af Revert "Fix crash when next_info is empty and using recurrent" 5 年前
GitHub b7e12a37 Fix crash in construct_curr_info when next_info doesn't have any agents (#2549) 5 年前
GitHub 3683cc1c Enable learning rate decay to be disabled (#2567) 5 年前
GitHub d21be895 Develop allow python 3.7 (#2544) 5 年前
GitHub babe9e2f Develop remove academy done (#2519) 5 年前
GitHub 832e4a47 Normalize observations when adding experiences (#2556) 5 年前
GitHub 67d754c5 Fix flake8 import warnings (#2584) 5 年前
Ervin Teng 02c8507b Add tensorboard startup on training 5 年前
Ervin Teng 3162606f Freeze support for multiprocessing 5 年前
GitHub 0d48a352 Use argparse for arg parsing (#2586) 5 年前
Ervin Teng 209c71c0 Move freeze support 5 年前
Ervin Teng dc47efbe Import webfiles.zip for Tensorboard 5 年前
GitHub d64a01e1 Added option to use environment arguments in learn (#2594) 5 年前
GitHub 36ed3c16 Fix issue exporting graph with multi-GPU (#2573) 5 年前
GitHub 149ebd67 Fix crash with VAIL + GAIL (#2598) 5 年前
Chris Elion 3cb1755e When checking for the compatibility of the expert brain with the policy brain, we will remove the action descriptions from the dictionary of things we need to compare. This is to prevent the case where a user has different descriptions for his actions but still wants to train a brain using expert demonstrations. (#2517) 5 年前
GitHub 473a8758 Develop yaml json loading errors (#2601) 5 年前
GitHub 6f9a2dfa Tick version of API and pypi packages to 10 (#2610) 5 年前
GitHub cb144f20 small mypy cleanup (#2637) 5 年前
Jonathan Harper 3fc14963 EXPERIMENTAL horovod support 5 年前
GitHub 2f74b3cc Rename protobuf objects to be suffixed with 'Proto' in python and C#. (#2646) 5 年前
Jonathan Harper 47893e9c minor tweaks 5 年前
GitHub b2fa2268 Merge pull request #2648 from Unity-Technologies/release-0.10.0 5 年前
GitHub 8e931d8d Merge branch 'develop' into release-0.10.0 5 年前
GitHub d1ebca5c Merge pull request #2649 from Unity-Technologies/release-0.10.0 5 年前
GitHub 4980b904 Cleanup visual obs setup (#2647) 5 年前
Chris Elion aa7cbaf7 Modified meta_curriculum JSON reading loop to only deal with .json (#2651) 5 年前
Ervin Teng 094cbe4d Fix bug when batch size is a non-multiple of sequence length (#2661) 5 年前
Anupam Bhatnagar cc208c00 resolving conflicts 5 年前
Ervin Teng e826f4bb Bugfix for LSTM+BC (#2679) 5 年前
Ervin Teng 35669d27 Fix SAC + LSTM Barracuda inference (#2698) 5 年前
GitHub 68965c7b Use a class for camera res, not dict (#2656) 5 年前
Ervin Teng df44ee8d Fix crash in trainer tests (trainer_metrics) 5 年前
GitHub 5f5ccfa0 Feature Deprecation : Online Behavioral Cloning (#2659) 5 年前
Chris Elion a64113ea rough pass at tf2 support, needs cleanup 5 年前
GitHub b2a2047e Fix bug when batch size is a non-multiple of sequence length (#2661) 5 年前
Chris Elion 43e23941 rough pass at tf2 support, needs cleanup 5 年前
Ervin Teng 024e3677 small mypy cleanup (#2637) 5 年前
Chris Elion 806c77e4 centralize tensorflow imports 5 年前
Ervin Teng bd5b3c7d Revert "Fix crash in trainer tests (trainer_metrics)" 5 年前
GitHub 24ba9d58 Develop deprecate broadcasting (#2669) 5 年前
Chris Elion 8da16bdb move compat functions 5 年前
Ervin Teng 005f312e Tick version numbers 5 年前
Chris Elion 1aa07606 fix imports for 1.14 5 年前
GitHub f22c41db Merge pull request #2704 from Unity-Technologies/hotfix-0.10.1 5 年前
GitHub e6240c7a Bugfix for LSTM+BC (#2679) 5 年前
Anupam Bhatnagar b733b34c resolving conflicts 5 年前
Chris Elion 73acf8a7 version check 5 年前
Chris Elion 6b54b0ca ban raw tensorflow imports 5 年前
Chris Elion a1967c19 Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
GitHub 39f280d6 Develop spawn brains (#2676) 5 年前
Chris Elion 1eee5b5c Barracuda hotfix for TF2 AddV2 support (#2703) 5 年前
GitHub 9bac2771 Fix SAC + LSTM Barracuda inference (#2698) 5 年前
Chris Elion 254c7d86 Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
GitHub 7e68f08f Merge Hotfix 0.10.1 to Develop (#2708) 5 年前
GitHub b51ccb52 Develop unified version (#2712) 5 年前
GitHub b95c4d1d check for unecessary list comprehensions (#2707) 5 年前
GitHub b15eeb8b Revert "Develop unified version (#2712)" (#2719) 5 年前
GitHub 5d3e05d1 Fix "memory leak" during inference (#2722) 5 年前
GitHub 619465e1 Fix crash when SAC is used with Curiosity and Continuous Actions (#2740) 5 年前
Chris Elion c531f87d Added --cpu flag to train using CPU only (#2755) 5 年前
GitHub 5ee487e9 Fixing unecerrary error with curriculum (#2772) 5 年前
GitHub 0892ef2c [WIP] ISensor interface and use for visual observations (#2731) 5 年前
Chris Elion 3dc677ee add VERSION variable to each setup.py 5 年前
Chris Elion 229d0cc3 update setups and config 5 年前
GitHub 0438acbf Deploy new versions to pypi (#2789) 5 年前
Ervin Teng 12a1e306 start on tf2 policy 5 年前
Jonathan Harper c5b94751 Bump version to 0.11.0.dev0 5 年前
Ervin Teng e185844f Start on TF 2 policy 5 年前
Chris Elion 3d8a70fb Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
Jonathan Harper 6fb6bb4c Update package and communicator versions to 0.11 5 年前
Jonathan Harper 4cdc7b29 Bump version to 0.11.0.dev0 5 年前
Chris Elion 6d245128 temp force 2.0 5 年前
GitHub 0fe5adc2 Develop remove memories (#2795) 5 年前
Chris Elion bcc5f9a0 numpy bump 5 年前
Chris Elion 13688e75 fix url in comments 5 年前
Anupam Bhatnagar f36a583c upgrading to tf-gpu 5 年前
Jonathan Harper f4c14d1d Remove filters / 0.11.0.dev3 5 年前
GitHub 6ba6f08c Merge 0.11.0 to develop (#2825) 5 年前
Anupam Bhatnagar d9910ee7 Merge branch 'develop' into develop-gpu-test 5 年前
GitHub 495873e5 Merge pull request #2833 from Unity-Technologies/release-0.11.0 5 年前
Chris Elion 691d21e6 Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
GitHub c6c01a03 Enable pylint and fix a few things (#2767) 5 年前
Jonathan Harper 8550679d Merge branch 'develop' into release-0.11.0 5 年前
GitHub d39b1881 speed up unit test (#2847) 5 年前
GitHub 4da157fe more pylint fixes (#2842) 5 年前
GitHub ccb7eab4 Remove {text,custom} {action,observations} (#2839) 5 年前
GitHub e6f549dc [MLA-12] update protobuf for vector observations (#2862) 5 年前
Chris Elion fca51de8 Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
GitHub bf68edcf ingore attribute-defined-outside-init in multi_gpu_policy (#2876) 5 年前
Chris Elion 73a346cb cleanup 5 年前
Chris Elion 89ad0106 undo hacks 5 年前
GitHub f57b7ac6 Allow usage with tensorflow 2.0.0 (via tf.compat.v1) (#2665) 5 年前
Chris Elion 7353ad22 Merge remote-tracking branch 'origin/develop' into try-tf2-support 5 年前
Ervin Teng 987e0e3a Merge tf2 branch 5 年前
Ervin Teng 748c250e Somewhat running 5 年前
Andrew Cohen 13fe9cf8 Bubbled up indexing of AllBrainInfo to trainer controller from trainers 5 年前
Ervin Teng 9dbbfd77 Somewhat running 5 年前
Andrew Cohen b11f04ea Fixed test code by creating brain_name variable instead of hardcoding 5 年前
Ervin Teng 5e6de46f Add normalizer 5 年前
GitHub c0453ae1 Merge pull request #2912 from Unity-Technologies/develop-allbraininfo 5 年前
Ervin Teng 5e1c1a00 Tweaks to Policy 5 年前
GitHub 99981937 fix errors from new flake8-comprehensions (#2917) 5 年前
Ervin Teng a665daed It's mostly training 5 年前
Andrew Cohen 184af227 splitting brain params into brain name and identifiers 5 年前
Ervin Teng 3eb1e9c2 Pytorch port of continuous PPO 5 年前
Ervin Teng d46b60b3 Add ReLU to the dense 5 年前
GitHub 38d39e38 disable tensorflow warnings by default (#2931) 5 年前
Ervin Teng ed2c35b9 Remove some comments 5 年前
Ervin Teng 135a5bb4 Add dummy save methods 5 年前
GitHub 69d1a033 Develop remove past action communication (#2913) 5 年前
Andrew Cohen e96b80db recieves brain_name and identifier on python side 5 年前
Ervin Teng 437c6c2f Add dummy save methods 5 年前
Ervin Teng d983a636 Speed up a bit faster 5 年前
Ervin Teng 54644477 Merge branch 'develop' of github.com:Unity-Technologies/ml-agents into develop-nomaxstep-test 5 年前
GitHub 28dbf4c5 Allow --version argument in mlagents-learn (#2942) 5 年前
Ervin Teng df5ee7bf Split buffer into two buffers (PPO works) 5 年前
GitHub a2194ea7 Fix batch size issue with BC (#2965) 5 年前
GitHub c57884dc bump version strings (#2955) 5 年前
Ervin Teng e5459c49 buffer split for SAC 5 年前
GitHub 2c7e6d51 Fix bug where constant LR in pretraining will throw TF error (#2977) 5 年前
Ervin Teng 9053610f Fix buffer tests and truncate 5 年前
GitHub b5eb34dc Fix batch size issue with BC (#2965) (#2966) 5 年前
Ervin Teng 29cdf77a Fix RL tests 5 年前
GitHub ece9733c add timers and fix filehandle leak (#2989) 5 年前
Ervin Teng a80b47d1 Fix demo loader and remaining tests 5 年前
Ervin Teng 3a4fa244 Switch to tanh squash in PPO 5 年前
Ervin Teng c5b23f46 Remove MANIFEST file 5 年前
Ervin Teng c2d216ca Add type hints to Buffer 5 年前
Andrew Cohen 94366bfe splitting brain params into brain name and identifiers 5 年前
GitHub b1dc1015 Fix bug where constant LR in pretraining will throw TF error (#2978) 5 年前
Ervin Teng fd0647a6 Rename append_update_buffer to append_to_update_buffer 5 年前
GitHub d6f69c1f handle null action outputs (#2988) 5 年前
Ervin Teng 73000a6b Merge branch 'develop' into develop-splitbuffer 5 年前
Andrew Cohen bd056007 recieves brain_name and identifier on python side 5 年前
Ervin Teng 3434352a Non-working commit 5 年前
Chris Elion c9e85137 dev version 5 年前
Ervin Teng 02b5e1ef Revert buffer for now 5 年前
Ervin Teng 17dca3ce Another nonworking commit 5 年前
Chris Elion 9ef661db fix tags 5 年前
Ervin Teng 1e36028d Runs but doesn't do anything yet 5 年前
GitHub a4c111f4 Merge pull request #3012 from Unity-Technologies/release-0.12.0-to-develop 5 年前
GitHub d4780a55 Merge pull request #3010 from Unity-Technologies/release-0.12.0-to-master 5 年前
GitHub 652488d9 check for numpy float64 (#2948) 5 年前
GitHub 681093cf cherry pick PR#3032 (#3066) 5 年前
GitHub a71c67d9 better logging for ports and versions (#3048) (#3069) 5 年前
GitHub 213cd68d Split Buffer into processing and update buffers (#2964) 5 年前
Ervin Teng 34f9577c Merge branch 'develop' into develop-agentprocessor 5 年前
GitHub 8ec5ab62 Develop side channels: migrate reset parameters (#2990) 5 年前
Ervin Teng f008dac0 Use ProcessingBuffer in AgentProcessor 5 年前
Chris Elion d988fc66 bump version strings 5 年前
Ervin Teng 2c9376bc Convert to trajectory 5 年前
Ervin Teng 9e661f0c Looks like it's training 5 年前
Ervin Teng c2b729a6 Fix memory leak 5 年前
GitHub ef2514ba Develop cold fix recurrent (#3032) 5 年前
GitHub 35c995e9 Merge pull request #3038 from Unity-Technologies/develop 5 年前
Ervin Teng a97ffb47 Attempt reward reporting 5 年前
Andrew Cohen e648cbc8 splitting brain params into brain name and identifiers 5 年前
Ervin Teng 9c5fdd31 Stats reporting is working 5 年前
Ervin Teng eb4a04a5 Merge branch 'master' into develop-tanhsquash 5 年前
GitHub 3b4b0d55 Remove random normal epsilon (#3039) 5 年前
Ervin Teng e0e57188 Clean up some stuff 5 年前
Ervin Teng b501f75b reduce sum to do squashing properly 5 年前
Andrew Cohen 5097bcc0 recieves brain_name and identifier on python side 5 年前
GitHub e7bf6fff Close environment if step raises an exception. (#3043) 5 年前
Ervin Teng f94365a2 No longer using ProcessingBuffer for PPO 5 年前
Ervin Teng 8b3b9e6c Move trajectory and related functions to trajectory.py 5 年前
Ervin Teng 76abf968 Add back max_step logic 5 年前
GitHub a6df9f43 Develop new ll api (#3022) 5 年前
Ervin Teng 88b1123a Merge branch 'master' of github.com:Unity-Technologies/ml-agents into develop-agentprocessor 5 年前
Ervin Teng 2f82a550 Remove epsilon 5 年前
Andrew Cohen 2b192bc3 trainer_controller expects name_behavior_ids 5 年前
Ervin Teng 28eba789 Migrate SAC 5 年前
Andrew Cohen 8578b0b7 add_policy and create_policy separated 5 年前
GitHub 15050bc4 better logging for ports and versions (#3048) 5 年前
Ervin Teng f2b3cd7f Remove dead code 5 年前
Andrew Cohen ef2dfd4c adjusting tests to expect trainer.add_policy to be called 5 年前
GitHub 36048cb6 Moving Env Manager to Trainers (#3062) The Env Manager is only used by the trainer codebase. The entry point to interact with an environment is UnityEnvironment. 5 年前
Ervin Teng c9116ed2 Move some common logic to buffer class 5 年前
GitHub 42bea858 Improve mypy coverage by adding --namespace-packages (#3049) 5 年前
Ervin Teng 336ca456 Kill the ProcessingBuffer 5 年前
Andrew Cohen bd5e8434 fixed naming name_behavior_id 5 年前
Andrew Cohen 8f62c69e splitting brain params into brain name and identifiers 5 年前
Ervin Teng 3697e616 Convert BC (warning) might be broken 5 年前
GitHub 90db165f Add --namespace-packages to mypy for mlagents (#3075) 5 年前
Ervin Teng c7632aa7 Fix some bugs for visual obs 5 年前
GitHub 1fa07edb Remove Standalone Offline BC Training (#2969) 5 年前
Andrew Cohen 614d276f recieves brain_name and identifier on python side 5 年前
Ervin Teng 5ab2563b Fixes for recurrent 5 年前
GitHub f9935dc9 Release 0.12.1 (#3078) 5 年前
Ervin Teng 40bbe173 Better decoupling for agent processor 5 年前
GitHub 8ca0d810 Better error handling if trainer config doesn't contain "default" section (#3063) 5 年前
Andrew Cohen c7f283df splitting brain params into brain name and identifiers 5 年前
Ervin Teng 62d609f8 Fix some of the tests 5 年前
GitHub 2c3794a6 handle mismatch between brain and metacurriculum (#3034) 5 年前
Andrew Cohen 96922f84 recieves brain_name and identifier on python side 5 年前
Ervin Teng 3449b551 Add test for trajectory 5 年前
GitHub e06b8f31 Fix has_actions_for_brains check (#3087) 5 年前
Chris Elion fdc810ff move (first pass) 5 年前
Ervin Teng 38ff674e Fix BC and tests 5 年前
GitHub 58b6c7c2 Rename mlagents.envs to mlagents_envs (#3083) 5 年前
Chris Elion f5e6b0ed more cleanup 5 年前
Ervin Teng 27c2a55b Lots of test fixes 5 年前
Andrew Cohen 2e8e8ac3 splitting brain params into brain name and identifiers 5 年前
Ervin Teng 97d66e71 Remove BootstrapExperience 5 年前
Andrew Cohen 45009c1a recieves brain_name and identifier on python side 5 年前
Ervin Teng 324d217b Move agent_id to Trajectory 5 年前
Ervin Teng 77ff4822 Add back next_obs 5 年前
Jonathan Harper 9f166f9e Update tests to support pytest 5.x 5 年前
Chris Elion fe7327b4 test pypi setup 5 年前
Ervin Teng 43c0acfb Fix test again 5 年前
Chris Elion e0225665 .dev1 5 年前
Andrew Cohen 46f8f077 trainer_controller expects name_behavior_ids 5 年前
Ervin Teng 83126bb2 Fix PPO value tests 5 年前
GitHub 9f522176 Merge pull request #3097 from Unity-Technologies/develop-pytest5 5 年前
Andrew Cohen d1edbf43 add_policy and create_policy separated 5 年前
Ervin Teng 2b811fc8 Properly report value estimates and episode length 5 年前
Andrew Cohen 70357569 adjusting tests to expect trainer.add_policy to be called 5 年前
Ervin Teng 77aea4cd Fix np float32 errors 5 年前
GitHub 2fd305e7 Move add_experiences out of trainer, add Trajectories (#3067) 5 年前
Ervin Teng 9d1eff12 Fix one more np float32 issue 5 年前
Andrew Cohen e67e866e fixed naming name_behavior_id 5 年前
Ervin Teng c330f6f6 Merge branch 'master' into develop-agentprocessor 5 年前
GitHub 3de3c1f1 check min size for visual encoders (#3112) 5 年前
Andrew Cohen de902fbb passes all pytest and C# tests 5 年前
Ervin Teng 47f8fa7a Fix some import errors 5 年前
GitHub 2ac242f7 Remove TrainerMetrics and add CSVWriter using new StatsWriter API (#3108) 5 年前
Andrew Cohen 07420320 fixed printing nonsense 5 年前
Ervin Teng fdf9aea7 Make conversion methods part of NamedTuples 5 年前
Ervin Teng 6242b67d Add way to check if trajectory is done or max_reached 5 年前
GitHub 0b5b1b01 Develop magic string + trajectory (#3122) 5 年前
Ervin Teng ea49396a Add docstring 5 年前
GitHub c7da0139 Fix mypy errors in trainer code. (#3135) 5 年前
Andrew Cohen 082789ea Merge branch 'master' into develop-magic-string 5 年前
Ervin Teng e2b2f4be Address AgentProcessor comments 5 年前
Andrew Cohen 6a4e7cf9 added ppo/sac_policy attributes to keep up with master 5 年前
Ervin Teng bad47dad Allow None max steps 5 年前
GitHub e536c09c Remove unused tf.placeholder (#3138) 5 年前
Andrew Cohen b14680f1 fixing ci tests 5 年前
Ervin Teng 1bd791e5 Merge branch 'master' into develop-agentprocessor 5 年前
Andrew Cohen 3e76adbd fixing more ci tests 5 年前
Ervin Teng abc8ca9a Fix tests 5 年前
GitHub 7fbf6b1d add flake8-bugbear (#3137) 5 年前
GitHub 0d56f6ba Merge branch 'master' into develop-magic-string 5 年前
Ervin Teng e577d5ea Fix some mypy issues and remove unused code 5 年前
Andrew Cohen b28b3835 fixed default trainer_util test to expect brain_name 5 年前
Ervin Teng d263d5be Fix numpy import 5 年前
GitHub c794931d add __init__.py to ml-agents (#3151) 5 年前
GitHub 6291fc75 bump version strings (#3147) 5 年前
Andrew Cohen 654b0c79 Merge branch 'master' into develop-magic-string 5 年前
Ervin Teng 400811b7 Remove defaultdict that didn't make sense 5 年前
GitHub c6152459 Allow curricula to be created without files (#3145) 5 年前
Andrew Cohen c3a92afa fixing ci ppo_policy 5 年前
Ervin Teng 9e0ef912 Fixed value estimate bug 5 年前
GitHub bec2e8f0 Add Trajectory/Policy Queues, move Trainer logic to advance() (#3113) 5 年前
Andrew Cohen fc485077 fixed more ci problems/removed self.policies 5 年前
Ervin Teng 4981c856 Fix mypy issue 5 年前
Ervin Teng db743971 Move private methods out of trainer, simplify interface 5 年前
andrewcoh a4ce89f3 add __init__.py to ml-agents (#3151) (#3153) 5 年前
Andrew Cohen c8514c18 Merge branch 'master' into develop-magic-string 5 年前
GitHub 45010af3 Add stats reporter class and re-enable missing stats (#3076) 5 年前
GitHub e2ae7124 pass file mode to h5py.File() (#3165) 5 年前
Ervin Teng b3a4e641 Remove some vestigial code 5 年前
GitHub 83afc742 pass file mode to h5py.File() (#3165) (#3166) 5 年前
Ervin Teng 48793ec1 Fix test 5 年前
Ervin Teng 69e7eeac Normalize based on number of elements 5 年前
GitHub a488299f [MLA-345] float visual observations (#3148) 5 年前
Ervin Teng 0046ea2d Add comment 5 年前
GitHub bed7debf Fix issue with different decision intervals for different brains (#3181) 5 年前
Ervin Teng 3d25f9d2 Merge branch 'master' into develop-agentprocessor 5 年前
GitHub d798b1cb Prevent tf.Session() from eating up all the GPU memory (#3219) 5 年前
Ervin Teng 0040dc7f New way to update mean and var 5 年前
Jonathan Harper 481e0842 Remove the --num-runs option 5 年前
GitHub 0f35116d Bump version strings (#3224) 5 年前
Ervin Teng f80b1d12 Use running norm and std 5 年前
GitHub 5bc7531b Get step from policy (#3223) 5 年前
GitHub 29c91b14 update flake8 plugin version and fix warnings (#3180) 5 年前
Ervin Teng ce75b378 update flake8 plugin version and fix warnings (#3180) 5 年前
GitHub d985dded Merge branch 'master' into merge-release-0.13.0 5 年前
Ervin Teng c48ddcf2 Fix pre-commit error 5 年前
Andrew Cohen 4c260917 fix flake merge conflicts with master 5 年前
GitHub ad42705d Merge pull request #3185 from Unity-Technologies/merge-release-0.13.0 5 年前
GitHub b0a2a54f Add 'run-experiment' script, simpler curriculum config (#3186) 5 年前
Ervin Teng 35d73d1d Split value and policy networks 5 年前
Yuan Gao 0817c44b Moved the demo files 5 年前
GitHub b3d3a9d6 Merge pull request #3202 from Unity-Technologies/develop-move-demo 5 年前
Ervin Teng 98ed88b1 Merge branch 'master' into develop-separatevalue 5 年前
GitHub 4c241a80 Only send previous action and current BrainInfo (#3187) 5 年前
GitHub 0fe7e731 use absolute path in error (#3230) 5 年前
GitHub f058b18c Replace BrainInfos with BatchedStepResult (#3207) 5 年前
GitHub 56a67403 Fix lost trajectories when they are produced faster than they are consumed (#3233) 5 年前
GitHub a64e7850 Fix issue with BatchedStepResult with no agents (#3240) 5 年前
GitHub e73c2bcb convert yamato tests to python (#3239) 5 年前
Ervin Teng 03c750a7 Move some functionality to optimizer 5 年前
Chris Elion 45e6e53c Refactor file logic in demo_loader and add unit tests. (#3241) 5 年前
Ervin Teng 2c1ef594 Move some functionality to optimizer-black 5 年前
Ervin Teng 6688453b Move some functionality to optimizer-black 5 年前
Ervin Teng 91ffde5f More incremental steps to separation 5 年前
Ervin Teng cd74e51b More progress 5 年前
Ervin Teng 2373cae8 Move methods into common optimizer 5 年前
Ervin Teng 76ad64d7 Some more bugfixes 5 年前
GitHub 69e6578d Fix numpy warning when stats don't exist (#3251) 5 年前
Ervin Teng bc04f9dc Working continuous updates 5 年前
Ervin Teng 29f3330f Merge master into hotfix-0.13.1 5 年前
Ervin Teng 17dc17e5 Discrete PPO working 5 年前
Ervin Teng e83276f6 Fix PPO test 5 年前
GitHub d52fb483 Merge pull request #3264 from Unity-Technologies/hotfix-0.13.1 5 年前
Ervin Teng 2b63415e Clean up policy files 5 年前
GitHub ca96b293 Move advance() logic for environment manager out of trainer_controller (#3234) 5 年前
Ervin Teng 9ad99eb6 Combined model and policy for PPO 5 年前
GitHub 5ce669f9 add dev0 suffix to versions (#3268) 5 年前
Ervin Teng 3348bcef Commit init file 5 年前
GitHub 329b23e0 Fix extra summary being written when loading from checkpoint (#3272) 5 年前
Ervin Teng 6baaf980 Remove PPO model 5 年前
Ervin Teng e912fa47 Simplify creation of optimizer, breaks multi-GPU 5 年前
Ervin Teng 164732a9 Move optimizer creation to Trainer, fix some of the reward signals 5 年前
Ervin Teng abc98c23 Change reward signal creation 5 年前
Ervin Teng 151e3b1c Move policy to common location, remove epsilon 5 年前
Ervin Teng b61d2fa1 Fix some typing issues with curiosity 5 年前
Ervin Teng d9fe2f9c Unified policy 5 年前
Ervin Teng 0ef40c08 SAC CC working 5 年前
GitHub 590559e7 Make the Agent reset immediately after Done (#3291) 5 年前
GitHub 14193ada Self-play for symmetric games (#3194) 5 年前
GitHub 0ff8f9af Create ML-Agents Package (#3267) 5 年前
GitHub 65dbe0ec Move processing of steps after reset to advance() (#3271) 5 年前
Ervin Teng db249ceb Merge branch 'master' into develop-splitpolicyoptimizer 5 年前
Ervin Teng 28f7608f Clean up value head creation 5 年前
Ervin Teng b21b3d5c Use resamp policy for SAC 5 年前
Ervin Teng 6bbcf2d7 Add typing to value head creator 5 年前
Ervin Teng 1b6e175c Fix discrete SAC and clean up policy 5 年前
Ervin Teng a5caf4d6 Remove epsilon from everywhere 5 年前
GitHub e4394d2f Run training in yamato for a few steps (#3244) 5 年前
Ervin Teng 8e300036 Add some typing to optimizer 5 年前
Ervin Teng edeceefd Zeroed version of LSTM working for PPO 5 年前
Ervin Teng 649c4185 Zero out memory 5 年前
Ervin Teng 9b7499a0 Revert learn.py 5 年前
Ervin Teng 4de71b84 0 out value estimates as well 5 年前
Ervin Teng 7f53bf8b Cleanup LSTM code 5 年前
Ervin Teng 5ec49542 SAC LSTM isn't broken 5 年前
Ervin Teng 08cb91de Remove __init__ for LearningModel static class 5 年前
Ervin Teng 7d616651 Add burn-in for memory PPO 5 年前
Ervin Teng 4871f49c Fix comments for PPO 5 年前
Ervin Teng cfc2f455 Fix BC and tests 5 年前
Ervin Teng a6e28cf4 Fix for visual obs 5 年前
Ervin Teng 78671383 Move initialization call around 5 年前
Ervin Teng cadf6603 Fix SAC CC and some reward signal tests 5 年前
Ervin Teng aec5fcc0 Fix policy tests 5 年前
Ervin Teng 85249afc Fix SAC scoping 5 年前
GitHub dd86e879 Separate out optimizer creation and policy graph creation (#3355) 5 年前
Ervin Teng 1f094da9 Fix policy's scoping 5 年前
Ervin Teng cdd57468 Re-fix scoping and add method to get all variables 5 年前
Ervin Teng 2eda5575 Fix discrete scoping 5 年前
Ervin Teng dc43b0c6 Add test for NN policy 5 年前
Ervin Teng d02bfbd4 Remove PPO policy tests 5 年前
Ervin Teng 1c4f60d4 remove more PPO tests 5 年前
GitHub bde6cfaf Update docs to reflect new package installation workflow. (#3362) 5 年前
Ervin Teng 48b39b80 Fix ghost trainer and all tests 5 年前
GitHub 63959125 backport tf2bc changes from barracuda-release (#3341) 5 年前
Ervin Teng cb2d2526 Reformat using black 5 年前
Ervin Teng dcbb90e1 Fix graph init in ghost trainer 5 年前
Ervin Teng 7a401feb Remove float64 numpy 5 年前
Ervin Teng 5f00782b Clean up some SAC LSTM 5 年前
GitHub 77c3c343 Updating version number (#3367) 5 年前
GitHub 2d13481c Updating version number (#3366) 5 年前
GitHub b8bfc79c set package and API to 0.15.0-dev0 (#3369) 5 年前
Anupam Bhatnagar 07c87f2c fixing version numbers on master branch 5 年前
GitHub 34792205 adding init to ghost trainer directory (#3381) 5 年前
Ervin Teng d4ee7346 Merge commit 'f9c05a61d574305497789b5997f1ae3ea1b1ad3b' into develop-splitpolicyoptimizer 5 年前
Ervin Teng 1407db53 Fix Barracuda export for LSTM 5 年前
Ervin Teng 7bbd91ad Change logic to fix memory leak 5 年前
Ervin Teng 14720e2d Remove burn-in 5 年前
Ervin Teng 7b0f700b Add test for deletion calls 5 年前
Ervin Teng 328476d8 Move check for creation into nn_policy 5 年前
GitHub 25c41f83 adding init to ghost trainer directory (#3381) (#3382) 5 年前
Ervin Teng f64bdc4b Fix SAC RNN test 5 年前
Ervin Teng ce110201 Add optional burn-in for SAC as well 5 年前
Ervin Teng 632ff859 add init 5 年前
Ervin Teng cbfbff2c Split optimizer and TFOptimizer 5 年前
GitHub f62af526 Set logging level to INFO, was overridden by newer TF (#3358) 5 年前
Ervin Teng 4d94e180 Move optimizer to common folder 5 年前
GitHub 2ac92182 constant for editor port (#3396) 5 年前
GitHub 3939ca52 Change AgentProcessor logic to fix memory leak (#3383) 5 年前
Ervin Teng d969e013 Remove extra tf_optimizer 5 年前
Ervin Teng 7d5c1b0b Add docstring and make some methods private 5 年前
Ervin Teng f9c0f169 Delete extra tf_optimizer 5 年前
Ervin Teng 00017bab Temporarily remove multi-GPU 5 年前
Ervin Teng faa9c702 Fix one more test for multi_gpu 5 年前
Ervin Teng c68b5643 Remove multi_gpu from learn test 5 年前
Ervin Teng c350c6d8 Added enforcement of m_size to be divisible by 2 5 年前
GitHub 1f9d04f2 Fix clear update buffer when trainer stops training, add test (#3422) 5 年前
Ervin Teng 5bfc0b87 Update docstring 5 年前
Alphonso Crawford d106d497 Raise exception if path does not exist 5 年前
Ervin Teng 441e6a0c Add typing to optimizer, rename self.tf_optimizer 5 年前
Alphonso Crawford 615de041 Check if environment is launchable in learn.py 5 年前
Ervin Teng ffdc41bb Removed floating constants 5 年前
Alphonso Crawford b891a38b properly formatting within environment_launch_check 5 年前
GitHub f20a27e0 Clear agent processor properly on episode reset (#3437) 5 年前
Ervin Teng 7004604d Used NamedTuple for create normalization tensors 5 年前
Alphonso Crawford 2c14779c moving launch check to static method 5 年前
Anupam Bhatnagar c70d0243 [bug-fix] Empty ignored trajectory queues, make sure queues don't overflow (#3451) 5 年前
Anupam Bhatnagar d8c79f48 resolving merge conflicts 5 年前
Ervin Teng 8abd4129 Clean up nn_policy 5 年前
GitHub 9a4b151c Merge pull request #3441 from Unity-Technologies/master-into-release-0.14.0 5 年前
Alphonso Crawford cff1a003 pylint error resolution 5 年前
Anupam Bhatnagar 991bfefd [bug-fix] Use correct agent_ids for demo loader (#3464) 5 年前
Alphonso Crawford 51e947fe extra space aboe create environment factory 5 年前
Ervin Teng 7c0fa1c4 Remove action_holder placeholder 5 年前
Alphonso Crawford 40f1f6ed validate_environment_path 5 年前
Alphonso Crawford 2a154bf3 Moving env_strip to validate_environment_path 5 年前
GitHub 18e1d01b Update section name in changelog.md (#3499) 5 年前
Ervin Teng 5ef902bf Merge branch 'master' into develop-splitpolicyoptimizer 5 年前
GitHub 6876a1d6 [bug-fix] Empty ignored trajectory queues, make sure queues don't overflow (#3451) 5 年前
GitHub 587dd165 Support for ONNX export (#3101) 5 年前
GitHub b2a4b689 [bug-fix] Use correct agent_ids for demo loader (#3464) 5 年前
GitHub 423e8d80 Update the test demo (#3466) 5 年前
GitHub 3641293f Change checkpoint suffix to "ckpt" (#3470) 5 年前
GitHub be14dd42 Make the timer output format consistent (#3472) 5 年前
Andrew Cohen e4d776c3 Merge branch 'master' into soccer-fives 5 年前
Ervin Teng bcc25d59 Merge branch 'master' into develop-splitpolicyoptimizer 5 年前
Ervin Teng c9fbb111 Fix entropy calculation 5 年前
GitHub 472f9f0e Merge branch 'master' into develop-badEnvReturnCode 5 年前
Ervin Teng be9d772e Add option to not condition sigma on obs 5 年前
Alphonso Crawford 35e49f5d Using f-strings for exception strings 5 年前
Ervin Teng 0ab7aa58 Fix tensor names 5 年前
Alphonso Crawford 802593a2 Adding test for bad env_path on create_environment_factory 5 年前
Ervin Teng 1cfc461a Remove and rename tf_optimizer 5 年前
Alphonso Crawford 26d44958 Update test_bad_env_path 5 年前
Ervin Teng 30e4424c Fix PPO optimizer creation 5 年前
Alphonso Crawford 1a7f9ad0 change test_learn.py 5 年前
Ervin Teng 63463bd1 Make TF graph seed deterministic 5 年前
Ervin Teng 847725f1 extend meta curriculum test steps 5 年前
Ervin Teng ff607162 Move learning rate reporting 5 年前
Ervin Teng 88998fc9 Add add_policy docstrings 5 年前
GitHub 24145c22 Merge pull request #3438 from Unity-Technologies/develop-badEnvReturnCode 5 年前
Ervin Teng a990e5e8 Add docstrings for model 5 年前
Ervin Teng c735e722 Make create critic methods private 5 年前
GitHub c145e75b Split Policy and Optimizer, common Policy for PPO and SAC (#3345) 5 年前
Ervin Teng da6daebd Make create losses private 5 年前
Andrew Cohen 5b0aca29 Merge branch 'master' into soccer-fives 5 年前
Ervin Teng 14f2a7f2 Rename LearningModel to ModelUtils 5 年前
Ervin Teng 1156b9b3 Merge branch 'develop-splitpolicyoptimizer' into develop-removeactionholder 5 年前
Ervin Teng d57124b4 Merge 'master' into develop-removeactionholder 5 年前
Ervin Teng d6eb262c Rename resample to reparameterize 5 年前
Ervin Teng 23088088 Remove outdated comment 5 年前
Ervin Teng ac583acb Make value estimate method private 5 年前
Ervin Teng d680ed32 Fix metacurriculum test (for good) 5 年前
Ervin Teng 242e2421 Move encoder creation to separate function 5 年前
Ervin Teng 53c25fb1 Move one-hot out of policy and remove selected_actions 5 年前
Ervin Teng a73704bc Remove previous action from policy 5 年前
Anupam Bhatnagar e04fcd71 Merge branch 'master' into master-into-release-0.14.1 5 年前
Ervin Teng d10d27e2 Merge commit '9450d3fc0dda4547a14c5ed1b7e13fc6e3a15413' into develop-nopreviousactions 5 年前
Andrew Cohen bd78ec40 self-play assym hacked branch 5 年前
Andrew Cohen 8fe1a27d fixed save_snapshot 5 年前
Andrew Cohen 30725c27 2v1 soccer config and env 5 年前
GitHub 30a196eb Fix metacurriculum test (for good) (#3511) 5 年前
GitHub 97a1d4b1 [change] Remove the action_holder placeholder from the policy. (#3492) 5 年前
Andrew Cohen de73baa9 Merge branch 'master' into soccer-fives 5 年前
GitHub b2cc1c25 [bug-fix] Fix continuous LSTMs and add test (#3521) 5 年前
GitHub 7d954797 [change] Separate action outputs into OutputDistributions object (#3514) 5 年前
Andrew Cohen 94654de4 ghost controller 5 年前
GitHub f469cbb0 Simple1DEnv refactor and additional ghost trainer tests (#3537) 5 年前
GitHub e4177de0 [change] Organize trainer files a bit better (#3538) 5 年前
GitHub a6bf50db Revert obs to goal in simple 1d test (#3540) 5 年前
GitHub 323f104c [tests] LSTM end-to-end tests (#3544) 5 年前
GitHub 870338b4 [bug-fix] Fix issue with more than one continuous actions (#3547) 5 年前
Andrew Cohen 573b1f6d Merge branch 'master' into soccer-fives 5 年前
Andrew Cohen 0cc2956d write to proto 5 年前
GitHub bcce774f [tests] Visual observation tests (#3549) 5 年前
GitHub 213d2466 [bug-fix] Change Simple1DEnvironment to spawn new agent IDs on reset (#3558) 5 年前
Anupam Bhatnagar 8f4999d4 Adding a logging utility for improved logs 5 年前
Jason Bowman c3b15492 Modify demo loader to support gzip comression and reduce memory usage by seeking for individual reads 5 年前
Anupam Bhatnagar abc369a6 Adding a logging utility for improved logs 5 年前
GitHub cb153a0f [change] Change warning language when adversarial scene is used without self-play (#3561) 5 年前
Anupam Bhatnagar f4dbedcf removed extraneous logging imports and loggers 5 年前
Anupam Bhatnagar ee67c628 add log level as an argument to create logger 5 年前
Anupam Bhatnagar c2611126 uniformize log level for all loggers 5 年前
GitHub 86141eee Merge pull request #3560 from Unity-Technologies/new-logger 5 年前
Anupam Bhatnagar e8e0078e first commit 5 年前
Anupam Bhatnagar 07b15ae7 [skip-ci] small refactors 5 年前
Anupam Bhatnagar 56ffcedd [skip ci] adding horovod rank in log messages 5 年前
Anupam Bhatnagar 6b7b27c7 [skip ci] reformatting log message 5 年前
Anupam Bhatnagar e5b26708 [skip ci] Revert adding horovod rank in log messages 5 年前
Anupam Bhatnagar 455adc60 [skip ci] continue training until worker-0 is done 5 年前
Anupam Bhatnagar e49f186b removing logging statements 5 年前
GitHub e3af96ca Merge branch 'master' into develop-demo-load-seek 5 年前
GitHub b6e3fd67 [tests] Add additional unit tests (#3581) 5 年前
GitHub ffd8f855 [bug-fix] Fix crash when demo size is smaller than batch size (#3591) 5 年前
Chris Elion 7f2e815a Merge remote-tracking branch 'origin/master' into develop-sidechannel-usability 5 年前
Chris Elion fa5e7e6d Merge remote-tracking branch 'origin/master' into develop-BehaviorParams-public 5 年前
Chris Elion 0d65c600 top-level timers to see where time is going 5 年前
GitHub 70503a28 Merge pull request #3604 from Unity-Technologies/develop-more-timers 5 年前
GitHub ed2eb6ef [bug-fix] Fix entropy computation in MultiCategorialDistribution (#3607) 5 年前
GitHub 873ba7fd [bug-fix] Fix stats reporting for reward signals in SAC (#3606) 5 年前
GitHub c42a11c3 [change] Throw a proper error when sequence length is greater than batch size. (#3583) 5 年前
GitHub 94de596b [change] Remove concatenate in discrete action probabilities to improve inference performance (#3598) 5 年前
Andrew Cohen b1cfa74d Merge branch 'master' into develop-test-imitation 5 年前
Ervin Teng ce6ab0de Make progress bar class and add to trainer 5 年前
Ervin Teng bcf073bf Move console logging to ConsoleWriter 5 年前
Andrew Cohen e7836fb5 record demos 1d env 5 年前
Ervin Teng 0da08104 Add enlighten to setup.py 5 年前
Ervin Teng 98d5b8e3 Add test 5 年前
Andrew Cohen 7aaf1fb6 gail and bc tests 5 年前
Ervin Teng 6b578de4 Merge branch 'develop-refactorprint' into develop-progress-bar 5 年前
Andrew Cohen f1eeed9c success threshold to .9 for imitation 5 年前
Ervin Teng 49df4038 Make progress bar a statswriter 5 年前
GitHub 0a8b30e9 Bumping version on the release (#3615) 5 年前
Andrew Cohen f6d6e3d0 reccurent gail tests 5 年前
Chris Elion 9c5fc33a enforce onnx conversion (expect tf2 CI to fail) (#3600) 5 年前
GitHub acbfa95d enforce onnx conversion (expect tf2 CI to fail) (#3600) 5 年前
GitHub 88c2bc66 Update error message 5 年前
GitHub 557678a0 Merge pull request #3628 from Unity-Technologies/release-0.15.0-onnx-CI 5 年前
GitHub d9274b7e Bumping versions on master (#3614) 5 年前
Chris Elion a5dd261b make sure top-level timer is closed before writing 5 年前
GitHub 320175d5 [change] Move console printing to StatsWriter class (#3616) 5 年前
GitHub a1f00b07 Merge pull request #3629 from Unity-Technologies/develop-timers-fix-writing 5 年前
Chris Elion d73125d6 make sure top-level timer is closed before writing 5 年前
GitHub 25cc9f15 [change] Move hyperparameter printing entirely into StatsWriters (#3630) 5 年前
GitHub 188d8589 Merge pull request #3631 from Unity-Technologies/release-0.15.0-fix-stats 5 年前
Chris Elion 58065a41 sanitize gauge names 5 年前
GitHub b5cd91ba Merge pull request #3635 from Unity-Technologies/sanitize-gauge-names 5 年前
GitHub ec278616 Hotfixes for Release 0.15.1 (#3698) 5 年前
GitHub 2912c883 Basic and visual GAIL and BC integration tests (#3626) 5 年前
Andrew Cohen 53bea15c Merge branch 'master' into soccer-fives 5 年前
Andrew Cohen ac261e36 Merge branch 'master' into self-play-mutex 5 年前
GitHub e13c89f5 enforce min coverage % (#3642) 5 年前
GitHub 6709a9bf [change] Clean up trainer interface, clean up GhostTrainer stats (#3634) 5 年前
GitHub 2ecd1d9b remove obsolete code, offset worker seeds (#3645) 5 年前
Andrew Cohen eefc4811 Merge branch 'master' into self-play-mutex 5 年前
Andrew Cohen 9f09a65d team id centric ghost trainer 5 年前
GitHub ceaac645 [tests] Make subprocess manager test easier (#3651) 5 年前
Andrew Cohen 79076b70 ELO calculation done in ghost controller 5 年前
Andrew Cohen 03b40795 removed opponent elo from stat collection 5 年前
Andrew Cohen 579bbd88 passing all tests locally 5 年前
Andrew Cohen 66b505c3 fixed controller behavior when first team discovered isnt 0 5 年前
Andrew Cohen 1a6e99bb save step on trainer step count/swap on ghost 5 年前
Ervin Teng 293579dd Use steps_per_update to determine SAC train interval 5 年前
Andrew Cohen 072b4135 soccer 2v1 on the cloud 5 年前
Andrew Cohen 54ad09a3 urllib parse 5 年前
GitHub 29f82921 [bug-fix] Improve performance for PPO with continuous actions (#3662) 5 年前
Ervin Teng 0fa2f4f7 Don't count buffer_init_steps 5 年前
Ervin Teng dbf8f7a5 Fix comment 5 年前
Andrew Cohen fb993986 Merge branch 'master' into self-play-mutex 5 年前
Ervin Teng ee27e2cc Fix tests 5 年前
Andrew Cohen 1269b555 docstrings/ghost_swap -> team_change 5 年前
Ervin Teng 3deb8e30 Make trainer in separate threads 5 年前
Andrew Cohen b42c9482 Merge branch 'self-play-mutex' into soccer-2v1 5 年前
Andrew Cohen c4e54218 replaced ghost_swap with team_change in tests 5 年前
GitHub 5d4f7f08 cleanup port logic in UnityEnvironment (#3673) 5 年前
Ervin Teng 93351d30 Fix comments 5 年前
Andrew Cohen d9cdb582 Merge branch 'self-play-mutex' into soccer-2v1 5 年前
Andrew Cohen b15a8b75 docstrings for all ghost trainer functions 5 年前
GitHub 104f2c46 [tests] Add tests for multiple actions/action branches (#3672) 5 年前
Ervin Teng e4d1df01 Fix TC test 5 年前
Andrew Cohen cbba8f52 SELF-PLAY NOW SUPPORTS MULTIAGENT TRAINERS 5 年前
GitHub de3fc4e8 Hotfix memory leak on Python (#3664) 5 年前
Andrew Cohen