安全な強化学習

| Topic path: Top / 強化学習 / 安全な強化学習

安全な強化学習に関するメモ

*サーベイ論文 [#s1eda9e8]

-[[García J and Fernández F (2015). ''A comprehensive survey on safe reinforcement learning''. JMLR 16(42):1437–1480.>https://jmlr.org/papers/v16/garcia15a.html]]
--安全な強化学習に関する最初のサーベイ論文
-[[Brunke L, Greeff M, Yuan Z, et al. (2022). ''Safe learning in robotics: From learning-based control to safe reinforcement learning''. Annual Review of Control, Robotics and Autonomous Systems 5:411–444. doi: 10.1146/annurev-control-042920-020211>https://doi.org/10.1146/annurev-control-042920-020211]]
--安全な強化学習に関するサーベイ論文
-[[Zhao W, He T, Chen R, et al. (2023). ''State-wise safe reinforcement learning: A survey''. IJCAI 2023 Survey Track:6814–6822. doi: 10.24963/ijcai.2023/763>https://doi.org/10.24963/ijcai.2023/763]]
--安全な強化学習に関するサーベイ論文。状態ごとに制約付きのMDP (State-wise Constrained MDP)

*論文 [#ke1f2355]
-[[Ray A, Achiam J, and Amodei D (2019). ''Benchmarking safe exploration in deep reinforcement learning''. Available from https://openai.com/research/benchmarking-safe-exploration-in-deep-reinforcement-learning>https://openai.com/research/benchmarking-safe-exploration-in-deep-reinforcement-learning]]
-[[Ray A, Achiam J, and Amodei D (2019). ''Benchmarking safe exploration in deep reinforcement learning''. Available from https://openai.com/research/benchmarking-safe-exploration-in-deep-reinforcement-learning>https://openai.com/research/benchmarking-safe-exploration-in-deep-reinforcement-learning]]
--OpenAI Safety Gymに関する論文


*Workshop [#t1fd796b]
-[[''Safe RL 2022''>https://saferl.online/2022/]]
--The 1st International Workshop on Safe Reinforcement Learning Theory and its Applications, IEEE MFI 2022

*Web [#ncb28416]
-[[chauncygu (2023). ''Safe reinforcement learning baselines''. GitHub [cited at 2023 Dec 19]. Available from https://github.com/chauncygu/Safe-Reinforcement-Learning-Baselines>https://github.com/chauncygu/Safe-Reinforcement-Learning-Baselines]]
--安全な強化学習に関する情報をまとめたGitHubページ



*コード [#h1b5e37c]
-[[OpenAI (2019). ''Safety Gym''. [cited at 2023 Dec 19]. Available from  https://openai.com/research/safety-gym>https://openai.com/research/safety-gym]]
--OpenAIが開発した安全な強化学習に関するベンチマーク環境
-[[OpenAI (2019). ''Safety starter agents''. GitHub. [cited at 2023 Dec 19]. Available from https://github.com/openai/safety-starter-agents>https://github.com/openai/safety-starter-agents]]
--OpenAIが用意した安全な強化学習エージェント
トップ   編集 差分 バックアップ 添付 複製 名前変更 リロード   新規 一覧 単語検索 最終更新   ヘルプ   最終更新のRSS