OpenUse Altair inside a notebook to display benchmark resultsdocumentationgood first issuethu-ml/tianshou #1,136 opened May 4, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available3 comments0 reactions0 assignees
OpenDon't pass envpool envs where vectorenvs are neededbuggood first issuerefactoringthu-ml/tianshou #1,096 opened Apr 3, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · No comments yetNo assignee yetNo comments yetHas a beginner-friendly labelContributing guide available0 comments0 reactions0 assignees
OpenReduce duplication between examples/atari/atari_network and examples/vizdoom/networkgood first issuerefactoringthu-ml/tianshou #1,092 opened Apr 3, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available1 comment0 reactions0 assignees
OpenSupport Dict observation spacesdocumentationenhancementgood first issuetentativethu-ml/tianshou #1,065 opened Feb 26, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available8 comments0 reactions0 assignees
OpenCode duplication between ReplayBuffer and ReplayBufferManagergood first issuerefactoringthu-ml/tianshou #1,057 opened Feb 16, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · No comments yetNo assignee yetNo comments yetHas a beginner-friendly labelContributing guide available0 comments0 reactions0 assignees
OpenInclude parts of atari/mujoco helpers in package codegood first issueminorrefactoringthu-ml/tianshou #988 opened Nov 8, 2023 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available1 comment0 reactions0 assignees
OpenRNN related issuesRNNbughelp wantedthu-ml/tianshou #937 opened Sep 7, 2023 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available12 comments0 reactions0 assignees
OpenExtend and fix reward/return normalizationsenhancementgood first issuethu-ml/tianshou #927 opened Aug 29, 2023 · Python · 7,121 starsWhy recommendedNo assignee yet · No comments yetNo assignee yetNo comments yetHas a beginner-friendly labelContributing guide available0 comments0 reactions0 assignees
OpenNeed a flexible method to record training data in TensorBoardenhancementgood first issuethu-ml/tianshou #895 opened Jun 29, 2023 · Python · 7,121 starsWhy recommendedHas a beginner-friendly label · Contributing guide availableHas a beginner-friendly labelContributing guide available5 comments0 reactions1 assignee
OpenAllow finding the corresponding episode from a sample in reply bufferRNNenhancementgood first issuethu-ml/tianshou #881 opened Jun 1, 2023 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available1 comment1 reaction0 assignees
OpenHow to support multi-agent reinforcement learningMARLdiscussiongood first issuethu-ml/tianshou #121 opened Jul 9, 2020 · Python · 7,121 starsWhy recommendedHas a beginner-friendly label · Contributing guide availableHas a beginner-friendly labelContributing guide available34 comments1 reaction1 assignee
OpenUse Altair inside a notebook to display benchmark resultsdocumentationgood first issuethu-ml/tianshou #1,136 opened May 4, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available3 comments0 reactions0 assignees
OpenDon't pass envpool envs where vectorenvs are neededbuggood first issuerefactoringthu-ml/tianshou #1,096 opened Apr 3, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · No comments yetNo assignee yetNo comments yetHas a beginner-friendly labelContributing guide available0 comments0 reactions0 assignees
OpenReduce duplication between examples/atari/atari_network and examples/vizdoom/networkgood first issuerefactoringthu-ml/tianshou #1,092 opened Apr 3, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available1 comment0 reactions0 assignees
OpenSupport Dict observation spacesdocumentationenhancementgood first issuetentativethu-ml/tianshou #1,065 opened Feb 26, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available8 comments0 reactions0 assignees
OpenCode duplication between ReplayBuffer and ReplayBufferManagergood first issuerefactoringthu-ml/tianshou #1,057 opened Feb 16, 2024 · Python · 7,121 starsWhy recommendedNo assignee yet · No comments yetNo assignee yetNo comments yetHas a beginner-friendly labelContributing guide available0 comments0 reactions0 assignees
OpenInclude parts of atari/mujoco helpers in package codegood first issueminorrefactoringthu-ml/tianshou #988 opened Nov 8, 2023 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available1 comment0 reactions0 assignees
OpenRNN related issuesRNNbughelp wantedthu-ml/tianshou #937 opened Sep 7, 2023 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available12 comments0 reactions0 assignees
OpenExtend and fix reward/return normalizationsenhancementgood first issuethu-ml/tianshou #927 opened Aug 29, 2023 · Python · 7,121 starsWhy recommendedNo assignee yet · No comments yetNo assignee yetNo comments yetHas a beginner-friendly labelContributing guide available0 comments0 reactions0 assignees
OpenNeed a flexible method to record training data in TensorBoardenhancementgood first issuethu-ml/tianshou #895 opened Jun 29, 2023 · Python · 7,121 starsWhy recommendedHas a beginner-friendly label · Contributing guide availableHas a beginner-friendly labelContributing guide available5 comments0 reactions1 assignee
OpenAllow finding the corresponding episode from a sample in reply bufferRNNenhancementgood first issuethu-ml/tianshou #881 opened Jun 1, 2023 · Python · 7,121 starsWhy recommendedNo assignee yet · Has a beginner-friendly labelNo assignee yetHas a beginner-friendly labelContributing guide available1 comment1 reaction0 assignees
OpenHow to support multi-agent reinforcement learningMARLdiscussiongood first issuethu-ml/tianshou #121 opened Jul 9, 2020 · Python · 7,121 starsWhy recommendedHas a beginner-friendly label · Contributing guide availableHas a beginner-friendly labelContributing guide available34 comments1 reaction1 assignee