312 次代码提交 (23981dbf-ba08-4426-85cc-ab0383ad98d0)

作者 SHA1 备注 提交日期
Arthur Juliani 982fab41 Initial commit 7 年前
vincentpierre cde3c8f7 formating and added documentation 7 年前
Arthur Juliani cfceb9f4 Fix timestep for PPO.ipynb 7 年前
GitHub 410f8709 Merge pull request #4 from Unity-Technologies/ppo-timestep 7 年前
vincentpierre c4745ba7 fix on the socket timeout error on windows due to the use of signal.SIGALRM 7 年前
vincentpierre bddfb85e changed the connection to non-blocking 7 年前
GitHub a14c4a4f Merge pull request #9 from Unity-Technologies/socket-timeout-fix 7 年前
Alexander Scheurer 3152c971 --keep-checkpoints=<n> option for ppo.py 7 年前
GitHub 64037ccb Merge pull request #16 from ASPePeX/keep-checkpoints 7 年前
Arthur Juliani 2133d9cb Remove scipy from requirements 7 年前
Arthur Juliani 71591043 PPO additions and warnings 7 年前
vincentpierre e36b8bf0 added broadcast to the player and heuristic brain. 7 年前
Arthur Juliani 0c7debb9 Change tensorboard command to work on Windows 7 年前
vincentpierre 7118a209 bug fix : The environment only requests actions from external brains when unique 7 年前
vincentpierre e191fbef added warning in case no brins are set to external 7 年前
vincentpierre 65df8ae9 fix on the instanciation of coreBrains, 7 年前
vincentpierre 0df8326e minor fixes 7 年前
GitHub 15fea1be Update README.md 7 年前
GitHub daf205da Merge pull request #35 from Unity-Technologies/fix-docs 7 年前
GitHub aee5d336 Fix discrete state (#33) 7 年前
vincentpierre 3f85bb56 Merge branch 'master' into dev-broadcast 7 年前
Arthur Juliani cd3bfb87 Added worker-id flag and pass through to enviroment in order to more easily manage multiple running simulations. (#40) 7 年前
Arthur Juliani adac2683 Fix for multi-agent with observations 7 年前
Arthur Juliani c190eb22 Randomize ppo training batch 7 年前
vincentpierre 431fc43c Merge branch 'master' of https://github.com/Unity-Technologies/ml-agents into dev-broadcast 7 年前
GitHub 4b7e0d4b Make clear meaning of <env_name> 7 年前
vincentpierre 5cae720d modified Environment to send a specific error when no external brains are in the environment 7 年前
vincentpierre ac910514 initial commit of the curriculum with broadcast. Improved the Unity python handshake 7 年前
vincentpierre 360984c4 curriculum.json params must have 4 entries 7 年前
vincentpierre e8429059 bug fix for python3 7 年前
vincentpierre 250eb8e1 better checking of the format of the curriculum file 7 年前
vincentpierre d421a300 updated the tests of unityagents 7 年前
vincentpierre c16e0ac3 modified the socket to receive states and images of any size 7 年前
Arthur Juliani b6ce30bf Add curriculum support to PPO 7 年前
Arthur Juliani e6696ed3 Don't print 7 年前
Arthur Juliani 4a11c005 Add curriculum code to notebook and simplify 7 年前
Arthur Juliani 06d9bbec Log lesson in TensorBoard 7 年前
vincentpierre 3b00302a merging dev-broadcast-curriculum 7 年前
vincentpierre 22db3d64 added the modified files from dev-cooperative-env 7 年前
vincentpierre 2b8353b2 porting the changes on ppo.py and removing AgentMonitor.cs 7 年前
vincentpierre d71ee998 changes on the ppo.py 7 年前
vincentpierre 6e950cd3 Can now switch inference configuration on/off in the editor. Reintroduced the broadcast feature for the non-External brains. Introduced the API number to check the compatibility between Unity and Python. 7 年前
Arthur Juliani d1b81a32 Add push curriculum 7 年前
Arthur Juliani 51f23cd2 0.2 Update 7 年前
Arthur Juliani b56259f6 Fix cumulative reward (Unity) and Nan reward (python) bugs 7 年前
Arthur Juliani 5ef4be55 Fix curriculum smoothing, and use reward for push curriculum 7 年前
Arthur Juliani 216888ee Fixed to give lesson index parameter when start up (#179) 7 年前
vincentpierre cd1feef6 minor fix to the Notebook 7 年前
GitHub 59a2bbe0 Improve memory management (#180) 7 年前
vincentpierre 7b534423 updated tests 7 年前
vincentpierre ebaf5268 ignoring the Packages folder that is created in unity-environment for Unity version 2017.3 7 年前
vincentpierre 053c3739 Launching the environment with absolute path. Need testing on Windows and Linux 7 年前
vincentpierre 22bfd276 simplifications on launching from absolute path, 7 年前
GitHub 00534390 Refactored GridWorld (#225) 7 年前
Arthur Juliani 2a0e9e6f Fixed issue with unity environment not being found on MacOS (#236) 7 年前
Arthur Juliani 9ded88f3 Provide support with incompatible API 7 年前
Arthur Juliani 75ea16ff Add comments and alphabetize flags 7 年前
Arthur Juliani de700c3a Multi Brain Training and Recurrent state encoder (#166) 7 年前
Arthur Juliani adedd491 Initial support for multiple observations (#256) 7 年前
vincentpierre a54e459c partial fix on the lstm 7 年前
Arthur Juliani 5b8822a0 Bug fix multiple observations 7 年前
Arthur Juliani fc1b8a1b Fix academy reset out of order 7 年前
GitHub 51621334 State Stacking & Banan Environment (#262) 7 年前
Arthur Juliani ce2ce437 Added growth parameter to stop failing with allocation under windows for #277 (#278) 7 年前
vincentpierre d01bd6c2 the bytes file will besaved under the name of the environment, not its path 7 年前
vincentpierre b7f787f6 bug fix on range of observations 7 年前
Arthur Juliani 57a9ed38 Require tensorflow 1.4.1 (#315) 7 年前
vincentpierre 62089508 Modified the tests 7 年前
Arthur Juliani 7bf0c888 trainer will raise an error if the memory of the brain is set wrong (#273) 7 年前
Arthur Juliani 2d6254c3 Require TensoFlow 1.4.0 (#326) 7 年前
vincentpierre db3cb9df Merge branch 'development' into dev-logfile 7 年前
Arthur Juliani 3b8755d2 fixes on imitation trainer, now works with demo (#274) 7 年前
Arthur Juliani 98cebd82 Fix typo "leaning_rate" (#324) 7 年前
Arthur Juliani 54652c69 dev-logParam (#135) 7 年前
vincentpierre 539c081f modified the python side to read the logfile path from the academy parameters 7 年前
Arthur Juliani 94c20ef0 Curriculum documentation and improved Area code 7 年前
vincentpierre 5e1d05af added the logfile_path property to the environment class. Give a link to the logfile when the timeout error is launched. 7 年前
GitHub faa53e35 Fix observations on PPO trainer (#340) 7 年前
vincentpierre 34b6e786 made the UnityTimeOutException that reads into the logfile when available 7 年前
GitHub f8a8b112 Move epsilon generation into graph (#283) 7 年前
vincentpierre 50f91f66 use logging instead of print 7 年前
GitHub 36d58cee Add Seeding, MaxStepReached, and Bootstrapping fix (#303) 7 年前
vincentpierre 1bbaf0dd added test in test_unityagents.py for curriculum class 7 年前
GitHub e676017b Reorganize learn.py (#302) 7 年前
Arthur Juliani 6ad7f010 Fix for discrete control image observations 7 年前
Arthur Juliani 4418421a Rename variables in imitation trainer 7 年前
Arthur Juliani c42eff57 Misc fixes 7 年前
GitHub d1cf3030 Merge pull request #309 from Unity-Technologies/dev-imitation 7 年前
GitHub 8317a659 Behavioral Cloning & Trainers Reorg (#328) 7 年前
vincentpierre d8f74dc9 If reset does not take either config or progress, no information is logged. 7 年前
vincentpierre 41ab078d replaced actions with previous_actions in the BrainInfo object 7 年前
Arthur Juliani c21a391d Various bug fixed and changes 7 年前
GitHub e11dae1d Python Testing & Image Inference Improvements (#353) 7 年前
Arthur Juliani 9d26767d Instantiate training buffer with trainer 7 年前
GitHub 0277039d Fix Basic Environment & Discrete States (#356) 7 年前
eshvk 23981dbf [containerization] CPU based containerization to support all environments that don't use observations 7 年前
eshvk 403e4aef [cleanup] Use debug mode for some log messages 7 年前
eshvk 9345614c [cleanup] Use debug mode for some log messages 7 年前
eshvk b4bad6bb [Hotfix] Upgrade Tensorflow to 1.4.0 7 年前
eshvk 75a14ac8 [Hotfix] Upgrade Tensorflow to 1.4.0 7 年前
GitHub a3c7b426 Merge pull request #357 from Unity-Technologies/feature/containerization 7 年前
Arthur Juliani 85ae912d Dev docs (#361) 7 年前
Arthur Juliani b8a4f5f1 Add Hallway envronment to validate LSTM models 7 年前
eshvk 030ac5c5 [cleanup] Add a new type hint to call a dictionary of BrainInfo objects as an AllBrainInfo. Propagate this hint to all methods. Some pep8 cleanups. 7 年前
GitHub 989dea4a Merge pull request #132 from Unity-Technologies/dev-logfile 7 年前
GitHub 9ad4182e Merge pull request #366 from Unity-Technologies/feature/cleanup 7 年前
Arthur Juliani c3644f56 Buffer fix for properly masking gradients 7 年前
GitHub f8d27dc5 Merge branch 'development-0.3' into feature/LSTM2 7 年前
vincentpierre eaf0745f fix on the test script 7 年前
GitHub 2bba53b8 Merge pull request #367 from Unity-Technologies/feature/LSTM2 7 年前
GitHub 99103b29 Use `curr_brain_info` 7 年前
Arthur Juliani 827dca28 Fix typo in model vars 7 年前
GitHub f134016b On Demand Decision (#308) 7 年前
vincentpierre 36481ff2 removed the monitor display when training 7 年前
GitHub 69481d2d Imitation Learning Helper (#371) 7 年前
Arthur Juliani b4838a0f Version 0.2 7 年前
Arthur Juliani 1bf46a85 Add flags for normalization and variable layers 7 年前
Arthur Juliani 6c1c8220 Python2 fix 7 年前
GitHub dcf58f75 Feature/previous text action (#375) 7 年前
GitHub a809630f Add config for crawler, and change crawler scene (#376) 7 年前
Arthur Juliani 22d931c0 Add comments to Reacher and re-train model w/ epsilon needed 7 年前
vincentpierre 6c55017e [FixingPytests] Added the new Semantic and modified the pytest 7 年前
GitHub 0838c2bc Merge pull request #378 from Unity-Technologies/docs/semantics-internal-brain 7 年前
GitHub 26a1ed87 Merge pull request #380 from Unity-Technologies/dev-reacher-cleanup 7 年前
GitHub e0d5b1b0 Fix for when not using teacher helper (#379) 7 年前
GitHub a7c9096f [Semantics] Modified the placeholder names (#381) 7 年前
Vincent Gao 02df3b34 resolved conflicts 7 年前
GitHub cfc6bdc8 [Fix] The environment logs information about itself when lauched. (#395) 7 年前
Vincent Gao 621ba3af clarify the python docs and learn.py help message 7 年前
Vincent Gao 6806c801 resolved comments 7 年前
Vincent Gao 2f373c5a fixed the learn.py with a better way 7 年前
GitHub 0c6aaa1e Merge pull request #400 from Unity-Technologies/docs/python-api 7 年前
Vincent Gao 1bc43933 Merge branch 'development-0.3' into hotfix/issue#333 7 年前
GitHub 5bdef358 [Fix] Must take mean of entropy to avoid errors what number of agents change during training (#407) 7 年前
Marwan Mattar ba6911c3 Merge branch 'development-0.3' into dev-api-doc-academy 7 年前
GitHub 41d32aca [Bouncer Environment] Now in 3D (#408) 7 年前
GitHub bb82e25d Revamped Push Block (#404) 7 年前
Marwan Mattar bab02a21 Merge branch 'development-0.3' into dev-api-doc-academy 7 年前
GitHub 9ca530cd Soccer Twos Environment (#420) 7 年前
Marwan Mattar 095632d6 Added reference to Basics in Jupyter installation 7 年前
Marwan Mattar 20ce0286 Cleared notebook output. 7 年前
Joe Ward 86474d7a Merge remote-tracking branch 'origin/development-0.3' into docs-training-brains-etc 7 年前
GitHub c83b0e7d Merge pull request #435 from Unity-Technologies/docs/installation 7 年前
GitHub 848b8a58 Fix PPO regression (#434) 7 年前
GitHub f19739cb Update API version in anticipation of v0.3 release (#437) 7 年前
GitHub 4a7481a1 RayPercpetion, Push Block, and misc environment changes (#432) 7 年前
GitHub 16e04ee0 [BugFix] Updated the apiNumber in the pytests (#449) 7 年前
GitHub d8c09831 Feature/new wall jump (#446) 7 年前
Marwan Mattar 72a71a08 Merge branch 'development-0.3' into dev-api-doc-decision 7 年前
Joe Ward 9163a54a resolved merge conflict with dev-0.3 branch 7 年前
Vincent Gao 9066f399 updated the comments 7 年前
Vincent Gao 0df2f777 Used the comment's sentence 7 年前
GitHub 95366dc2 Merge pull request #460 from Unity-Technologies/docs/comment-change 7 年前
GitHub dede2f80 Modify setup file (#486) 7 年前
Marwan Mattar 06cc85cc Merge branch 'development-0.3' into docs/random-fixes 7 年前
GitHub 68692f8f Remove unused configs (#489) 7 年前
vincentpierre e5a59e9b [Refactor] renamed is_continuous to is_continuous_action and added is_continuous_observation to decrease confusion 7 年前
GitHub 6dd3c284 Hotfix 0.3.0b (#519) 7 年前
GitHub a6385cbf Merge pull request #536 from Unity-Technologies/master 7 年前
eshvk 2d2eb64b [containers] Enables container support for scenes that use visual observations 7 年前
Marwan Mattar ffb4ffee Added simple check to Python version in notebook. 7 年前
GitHub 74064891 Merge pull request #520 from Unity-Technologies/feature-trainer-ppo-is-continuous 7 年前
GitHub e43c069e Merge pull request #547 from Unity-Technologies/develop-feature-docker-improvements 7 年前
GitHub 02b189d4 Merge pull request #568 from Unity-Technologies/develop-improve-jupyter-notebook 7 年前
GitHub 237b41f9 Hotfix 0.3.0c (#618) 7 年前
GitHub 78d411f6 Merge pull request #619 from Unity-Technologies/develop 7 年前
GitHub 1a449e98 Hotfix 0.3.1b (#637) 7 年前
vincentpierre 076c8744 Report means instead of totals for losses (#580) 7 年前
GitHub b2675216 Hotfix 0.3.1b (#656) 7 年前
GitHub 755be43e [Cold Fix] Making the episode length and mean reward more accurate for the first episode (#657) 7 年前
GitHub 3b866e9f Use Clipped Gaussian (#649) 7 年前
Arthur Juliani 9477eaa9 Develop fix cumulative reward (#725) 7 年前
GitHub 9594f3d8 Walker Environment (#720) 7 年前
GitHub 38098a12 [Fixed BC with LSTM] (#766) 6 年前
Arthur Juliani ce5e2dba [Added Ascii art on learn.py] (#727) 6 年前
Arthur Juliani 0264de49 [Update Curriculum for WallJump] Updating the curriculum for WallJump (#774) 6 年前
GitHub ffcf8c9c Newer Ascii Art (#780) 6 年前
GitHub bdeb506c TensorFlowSharp 1.7 upgrade package (#746) 6 年前
GitHub 7914387f Develop communicator redesign (#638) 6 年前
GitHub 702d98c6 [Fix] The summary writer is now implemented in the abtract trainer class. (#806) 6 年前
GitHub c17937ef Curiosity Driven Exploration & Pyramids Environments (#739) 6 年前
GitHub 9ab98584 Additional Environment Variations (#791) 6 年前
Arthur Juliani 5abb001b [Add curiosity_enc_size: 128 to the trainer_config.yaml] (#826) 6 年前
vincentpierre a22c0f65 [fixing encoding_size] 6 年前
Arthur Juliani d7338050 Enable concurrent sessions 6 年前
vincentpierre 3c2283e8 [fix tennis] 6 年前
vincentpierre 85b844cc [Better version of the fix] 6 年前
GitHub 678e5dab Merge pull request #837 from Unity-Technologies/develop-fix-tennis 6 年前
eshvk 680b0767 [Imitation Learning] Minor fix to make sure that step increment loads from the last saved global step if the model is being trained after loading 6 年前
GitHub e195b495 Merge pull request #838 from Unity-Technologies/develop-bc 6 年前
Arthur Juliani 5d402be9 Minor Optimizations (#836) 6 年前
GitHub 282d5bd4 Fix Pytests (#843) 6 年前
GitHub 8526dcfc Fix for visual observations (#847) 6 年前
GitHub 0f65e272 [Addresses #842] (#849) 6 年前
GitHub a720e370 Fix bug and update tests (#850) 6 年前
GitHub c9c9e147 Revamp Crawler & Walker (#841) 6 年前
GitHub 47fc38ab Additional Tests & Bug Fixes (#854) 6 年前
GitHub 6e6e8d96 Fix for CC models w/ RNN and Curiosity (#860) 6 年前
vincentg 3c4cb523 some hack to make windows save the model when do ctrl+c 6 年前
GitHub 75218e58 Several final improvement to docs, scene and configs. (#871) 6 年前
GitHub b5722dc9 Fix for visual observation w/ curiosity (#873) 6 年前
GitHub 9156737e Merge pull request #876 from Unity-Technologies/release-windows-save-model-fix 6 年前
vincentpierre 4c6439d5 [Attempted fix] 6 年前
GitHub 6df07946 Fix for Discrete observations + Curiosity (#866) 6 年前
GitHub dda6ad8b Replaced message printed in Python and in documentation. (#881) 6 年前
GitHub 68d6170f Error message when using ODD and Curiosity (#883) 6 年前
GitHub bf858cd6 Merge pull request #884 from Unity-Technologies/release-v0.4 6 年前
GitHub 4b3c6c9f Merge pull request #885 from Unity-Technologies/release-v0.4 6 年前
Arthur Juliani 7b03597f Update setup version to v0.4 6 年前
Arthur Juliani 5e48766d Remove discrete observations 6 年前
GitHub 3eac018a Merge pull request #889 from Unity-Technologies/hotfix-setup-version 6 年前
Arthur Juliani b46b8708 Rename function 6 年前
Arthur Juliani 12d52cb0 Replace tanh on cc models w/ swish 6 年前
Arthur Juliani 96e599e1 New proto files 6 年前
Arthur Juliani 8088d94a Change lambda 6 年前
GitHub b6fe0bca Merge pull request #906 from Unity-Technologies/develop-no-discrete-obs 6 年前
Arthur Juliani 195ac934 Merge branch 'develop' into develop-runs 6 年前
vincentpierre e47cec56 [Initial Commit] 6 年前
Arthur Juliani fad0da30 Log run-id in console 6 年前
GitHub 1626587d Merge pull request #901 from Unity-Technologies/hotfix-swish 6 年前
Arthur Juliani 11b50054 Replace Ray with multiprocess 6 年前
Arthur Juliani fa65ee61 Fix bug in grpc logic 6 年前
unityjeffrey 0d67f311 changed ml agents to ml-agents 6 年前
Arthur Juliani e5202092 Remove empty line 6 年前
unityjeffrey 19fb437a changed to Unity ML-Agents Toolkit (english) 6 年前
unityjeffrey 6ed6b8d6 updated ml-agents to ml-agents toolkit where appropriate 6 年前
GitHub 7b9a2905 Merge pull request #916 from Unity-Technologies/hotfix-trademarkupdate 6 年前
Arthur Juliani 9701c3db Merge branch 'hotfix-0' into release-v0.4-fix-curiosity-odd 6 年前
Arthur Juliani 6b359062 Fix for visual-only imitation learning 6 年前
Arthur Juliani 0c6411c2 Use switch between old and new behavior 6 年前
GitHub 7b497341 Merge pull request #936 from Unity-Technologies/hotfix-visual-imitation 6 年前
Arthur Juliani 1bfbf67a Simplify approach 6 年前
Arthur Juliani cfb7cfef Code clean-up 6 年前
Arthur Juliani 083cbff5 Add to docstring 6 年前
Arthur Juliani c31f63b5 Fix typo 6 年前
GitHub 3b5af6b2 Merge pull request #937 from Unity-Technologies/release-v0.4-fix-curiosity-odd 6 年前
GitHub f155d661 Merge pull request #908 from Unity-Technologies/hotfix-0 6 年前
GitHub e50ac7ae Merge branch 'develop' into hotfix-0 6 年前
GitHub b36e6a2e Merge pull request #946 from Unity-Technologies/hotfix-0 6 年前
vincentpierre c104d31d [Hotfix] Made the Pipe of the grpc communicator an instance property 6 年前
Deric Pang 8380f2f2 Moved curriculum code out of environment code. 6 年前
Deric Pang 9b37b410 Removed test references to vector_observation_space_type. 6 年前
GitHub dcd4b4f9 Merge pull request #967 from dericp/develop-fix-python-tests 6 年前
Deric Pang e580e544 Removing commented out code. 6 年前
Deric Pang ae944381 Removing print statements. 6 年前
Deric Pang 6eb10797 Removed test references to vector_observation_space_type. 6 年前
GitHub 8d79581f Merge pull request #1001 from Unity-Technologies/hotfix-grpc-multiprocessing 6 年前
Deric Pang db031b07 Updating tests for refactored curriculum learning. 6 年前
Deric Pang 798c8bf9 Removing print statements. 6 年前
GitHub 59f74e07 Merge pull request #1002 from Unity-Technologies/hotfix-0.4b 6 年前
Deric Pang 7963f8ac Merge remote-tracking branch 'upstream/develop' into develop-curriculum-learning-refactor 6 年前
Deric Pang 134548ac Updating tests for refactored curriculum. 6 年前
Deric Pang d85038aa Removing some trailing spaces. 6 年前
GitHub 2d715dc5 Revert "Release v0.5 (#1202)" (#1221) 6 年前
Deric Pang eb251008 Removing unnecessary import. 6 年前
Deric Pang cd7c854c Created exception module for unitytrainers. 6 年前
GitHub 34035176 Merge pull request #968 from dericp/develop-curriculum-learning-refactor 6 年前
GitHub 4e73f770 Merge branch 'develop' into hotfix-0.4b 6 年前
GitHub a912e039 Merge pull request #1005 from Unity-Technologies/hotfix-0.4b 6 年前
Arthur Juliani 1eb701af Merge remote-tracking branch 'origin/develop' into develop-value-estimates-ppo 6 年前
Arthur Juliani f52d5a92 Merge remote-tracking branch 'origin/develop' into develop-runs 6 年前
Arthur Juliani 43e40b8c Add protobuf files for value estimate 6 年前
Arthur Juliani 3b916dd9 Add exception for in-edtior training 6 年前
GitHub 1e21c143 Merge pull request #934 from Unity-Technologies/develop-value-estimates-ppo 6 年前
Arthur Juliani ffe365dc Add white space 6 年前
GitHub ef3025e6 Merge pull request #1004 from Unity-Technologies/develop-runs 6 年前
GitHub e60272f2 New error when using In Editor Training with a non-zero worker-id (#1012) 6 年前
GitHub 7d0990cf Fix MultiBrain bug that was introduced with the value estimates (#1018) 6 年前
Deric Pang de128fa1 Refactoring Curriculum tests and code. 6 年前
Deric Pang c6617b70 Multi-curriculum support added. 6 年前
Deric Pang c754e9db Curriculum tests updated to match develop branch. 6 年前
Deric Pang 9ea00ab6 Changing curricula to match reworked curriculum. 6 年前
Deric Pang c88c7e42 Fixing bugs, updating tests. 6 年前
Deric Pang 10ab5965 Finished testing School. Added documentation. 6 年前
Deric Pang 06eb8037 Renaming School to MetaCurriculum. 6 年前
Deric Pang aaab8c50 Fix iteration over brains_to_curriculums. 6 年前
Deric Pang 645cd074 Moving push curriculum. 6 年前
Deric Pang 4b92071b Fixing line lengths in test_meta_curriculum.py. 6 年前
Deric Pang db6fa4ba Removing commented line. 6 年前
Deric Pang e678e691 Addressing Vince's offline comments. 6 年前
Deric Pang 361d56b9 Curriculums now hold the brain name. 6 年前
Deric Pang ca54fc4f Adding back import that was accidentally removed. 6 年前
Deric Pang ff4ce695 Updated logging in trainer. 6 年前
Deric Pang 9d9c91e4 Fixed TensorBoard lesson logging. 6 年前
Deric Pang 70308432 Adding space in metacurriculum error message. 6 年前
Deric Pang 4429077f Improving MetaCurriculum initialization. 6 年前
Deric Pang 23740545 Changing warning message to log.warning. 6 年前
GitHub 322d2bbe Merge pull request #1003 from dericp/develop-curriculum-learning-rework 6 年前
Deric Pang 822d329a Fixing bug when no curriculum folder is passed. 6 年前
GitHub 73ecb4fe Merge pull request #1035 from dericp/develop-fix-no-curriculum-case 6 年前
vincentpierre 7f74131d Nan Rewards converted to 0 and throwing a warning 6 年前
GitHub 5efa9d4e Merge pull request #1045 from Unity-Technologies/develop-unityagents-nan-reward 6 年前
Deric Pang 30c4f2d7 Splitting up unitytrainers tests. 6 年前
Arthur Juliani 52865022 [Fix bug 1040] (#1062) 6 年前
Deric Pang 032446de Trainer controller lines wrapped. 6 年前
Arthur Juliani 708e2bb9 Check NaN in observations (#1063) 6 年前
Deric Pang bb8e74f9 Helper func for incrementing lessons and resetting. 6 年前
Arthur Juliani 9e8049f0 Will now print summaries even when not training or when training is over (#1020) 6 年前
GitHub 9538d699 Move seed randomization to learn.py (#1071) 6 年前
Deric Pang 6eba6940 Merge remote-tracking branch 'upstream/develop' into develop-trainer-controller-cleanup 6 年前
GitHub 514cd757 Merge pull request #1058 from dericp/develop-trainer-controller-cleanup 6 年前
Arthur Juliani 3659bbcd Develop multi discrete (#1022) 6 年前
GitHub c600a706 Optional gym wrapper (#1007) 6 年前
Arthur Juliani fee02a84 Attempted fix for #1059 (#1089) 6 年前
Arthur Juliani 567ad3f0 fix Unity-Technologies/ml-agents#1041 (#1102) 6 年前
GitHub 2edaf342 Clean up learn.py (#1106) 6 年前
Arthur Juliani 17224292 Fix for Curiosity with ODD (#1107) 6 年前
GitHub ded0d8c7 Develop action masking (#1080) 6 年前
GitHub 9ba493ef Fixing develop after merging action masking (#1114) 6 年前
GitHub d0158b01 Update visual hyperparameters (#1118) 6 年前
GitHub 106d562d Fix for Windows (#1120) 6 年前
GitHub 2e489abc Normalization of the probabilities after masking (#1123) 6 年前