{"payload":{"feedbackUrl":"https://github.com/orgs/community/discussions/53140","repo":{"id":473891875,"defaultBranch":"main","name":"deep_rl_zoo","ownerLogin":"michaelnny","currentUserCanPush":false,"isFork":false,"isEmpty":false,"createdAt":"2022-03-25T06:19:07.000Z","ownerAvatar":"https://avatars.githubusercontent.com/u/56952187?v=4","public":true,"private":false,"isOrgOwned":false},"refInfo":{"name":"","listCacheKey":"v0:1668523586.7824671","currentOid":""},"activityList":{"items":[{"before":"1b5450eb403976be223daf80e29461bedd5d835b","after":"19e3844ccdd23f8e1c45482daf1bb9020c1bcaad","ref":"refs/heads/main","pushedAt":"2024-02-21T07:33:29.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"michaelnny","name":"Michael Hu","path":"/michaelnny","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/56952187?s=80&v=4"},"commit":{"message":"Update policy_gradient.py","shortMessageHtmlLink":"Update policy_gradient.py"}},{"before":"e06fd3f5e2b336197e71f91562757d9169701697","after":"1b5450eb403976be223daf80e29461bedd5d835b","ref":"refs/heads/main","pushedAt":"2023-07-30T08:27:07.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"michaelnny","name":"Michael Hu","path":"/michaelnny","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/56952187?s=80&v=4"},"commit":{"message":"Improve numerical stability for PPO, fix typos in NGU, Agent57","shortMessageHtmlLink":"Improve numerical stability for PPO, fix typos in NGU, Agent57"}},{"before":"cd860e80cb43c56efd494ea0ae4b358c5bed6ee2","after":"e06fd3f5e2b336197e71f91562757d9169701697","ref":"refs/heads/main","pushedAt":"2023-07-08T12:45:34.000Z","pushType":"push","commitsCount":1,"pusher":{"login":"michaelnny","name":"Michael Hu","path":"/michaelnny","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/56952187?s=80&v=4"},"commit":{"message":"fix bug when compute distance in episodic curiosity module","shortMessageHtmlLink":"fix bug when compute distance in episodic curiosity module"}},{"before":"ab3035134daa4e6f2d57758bd8a3a7e48bea5b53","after":"cd860e80cb43c56efd494ea0ae4b358c5bed6ee2","ref":"refs/heads/main","pushedAt":"2023-06-09T05:51:27.609Z","pushType":"push","commitsCount":1,"pusher":{"login":"michaelnny","name":"Michael Hu","path":"/michaelnny","primaryAvatarUrl":"https://avatars.githubusercontent.com/u/56952187?s=80&v=4"},"commit":{"message":"June 2023 major update with breaking changes\n\n- Support Python 3.10\n- Support Pytorch 2.0\n- Support running actors on multiple GPUs for distributed training\n- Improve performance for curiosity module\n- Refactor to adapt better parameter naming conventions\n- Refactor and clean up Atari environment wrappers, add visited rooms info for MontezumaRevenge and Pitfall\n- Fix bug where the RND for PPO implementation is wrong\n- Fix bug on Windows when initialize random seed using 2**32 exceeds int32 high bound\n- Temporarily fix TypeError with Python 3.10 when running distributed RL on classic environments and try to set seed through env.seed(seed)","shortMessageHtmlLink":"June 2023 major update with breaking changes"}}],"hasNextPage":false,"hasPreviousPage":false,"activityType":"all","actor":null,"timePeriod":"all","sort":"DESC","perPage":30,"cursor":"djE6ks8AAAAEAIe85QA","startCursor":null,"endCursor":null}},"title":"Activity · michaelnny/deep_rl_zoo"}