{"full_name":"openai/baselines","owner":"openai","name":"baselines","shard":"1","url":"https://github.com/openai/baselines","description":"OpenAI Baselines: high-quality implementations of reinforcement learning algorithms","homepage":"","topics":[],"tag_pages":[],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/14957082?v=4","created_at":"2017-05-24T01:58:13Z","pushed_at":"2024-08-01T21:31:33Z","metrics":{"stars":16780,"forks":4916,"watchers":621,"issues":850,"prs":376,"releases":0,"issues_open":413,"issues_closed":437,"prs_open":89,"prs_closed":112,"prs_merged":175,"discussions":0},"growth":{"day":{"stars":0,"forks":0,"base_day":"2026-11-15"}},"history":{"dates":["2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[16778,16779,16778,16778,16779,16780,16780],"forks":[4917,4917,4917,4917,4916,4916,4916],"watchers":[null,621,621,621,621,621,621],"issues_open":[null,413,413,413,413,413,413],"prs_open":[null,89,89,89,89,89,89]},"boards":{},"same_owner":[{"full_name":"openai/codex","name":"codex","shard":"1","boards":{"weekly":143,"monthly":101,"total":85}},{"full_name":"openai/whisper","name":"whisper","shard":"1","boards":{"daily_watchers":119,"total":117}},{"full_name":"openai/CLIP","name":"CLIP","shard":"1","boards":{}},{"full_name":"openai/chatgpt-retrieval-plugin","name":"chatgpt-retrieval-plugin","shard":"1","boards":{}},{"full_name":"openai/codex-plugin-cc","name":"codex-plugin-cc","shard":"1","boards":{}},{"full_name":"openai/codex-security","name":"codex-security","shard":"1","boards":{"weekly":67,"weekly_rate":75,"monthly_rate":163}},{"full_name":"openai/evals","name":"evals","shard":"1","boards":{}},{"full_name":"openai/gpt-3","name":"gpt-3","shard":"1","boards":{}},{"full_name":"openai/gym","name":"gym","shard":"1","boards":{}},{"full_name":"openai/math","name":"math","shard":"1","boards":{"new":24}},{"full_name":"openai/openai-cookbook","name":"openai-cookbook","shard":"1","boards":{"daily_watchers":127}},{"full_name":"openai/parameter-golf","name":"parameter-golf","shard":"1","boards":{}},{"full_name":"openai/shap-e","name":"shap-e","shard":"1","boards":{}},{"full_name":"openai/skills","name":"skills","shard":"1","boards":{}},{"full_name":"openai/tart","name":"tart","shard":"1","boards":{}},{"full_name":"openai/tiktoken","name":"tiktoken","shard":"1","boards":{}}],"issues":[{"number":121,"title":"Taking action limits into account in PPO/TRPO/ACKTR.","comments":37,"created_at":"2017-08-29T13:06:07Z"},{"number":431,"title":"Default hyperparamters for `run_atari.py` (using P-DDDQN) fail with Pong and Breakout (log files attached)","comments":34,"created_at":"2018-06-08T16:33:43Z"},{"number":162,"title":"Saving and restoring DDPG agent","comments":26,"created_at":"2017-10-09T18:57:29Z"},{"number":938,"title":"DDPG implementation fails to learn well on at least five MuJoCo-v2 envs for all three noise types. I report steps to reproduce and learning curve plots [and show that PPO2 seems to work fine].","comments":21,"created_at":"2019-06-20T16:50:38Z"},{"number":596,"title":"About Tensorboard","comments":21,"created_at":"2018-09-17T14:52:34Z"},{"number":176,"title":"Cannot reproduce Breakout benchmark using Double DQN","comments":15,"created_at":"2017-10-20T12:54:03Z"},{"number":608,"title":"`SubprocVecEnv` speedup does not scale linearly compared with `DummyVecEnv`","comments":14,"created_at":"2018-09-21T11:27:16Z"},{"number":240,"title":"Reference for DeepMind using FireResetEnv wrapper's functionality","comments":14,"created_at":"2017-12-30T19:47:09Z"}],"discussions":[],"latest_release":null,"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}