![](https://img-blog.csdnimg.cn/20201014180756928.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
李宏毅深度强化学习笔记
jessie_weiqing
https://github.com/seaweiqing
如果大家有感兴趣的论文,可以留言,会考虑根据留言出一些论文解读~
展开
-
【笔记2-4】李宏毅深度强化学习笔记(四)Actor-Critic
李宏毅深度强化学习- Actor-CriticAsynchronous Advantage Actor-Critic (A3C)Review – Policy GradientReview – Q-LearningActor-CriticPathwise Derivative Policy Gradient李宏毅深度强化学习课程 https://www.bilibili.com/video/a...原创 2019-02-27 20:13:15 · 8120 阅读 · 2 评论 -
【笔记2-5】李宏毅深度强化学习笔记(五)Sparse Reward
李宏毅深度强化学习- Sparse RewardReward ShapingCurriculum LearningHierarchical Reinforcement Learning李宏毅深度强化学习课程 https://www.bilibili.com/video/av24724071笔记更新中:李宏毅深度强化学习笔记(一)Outline李宏毅深度强化学习笔记(二)Proximal...原创 2019-02-27 21:07:29 · 4497 阅读 · 2 评论 -
【笔记2-6】李宏毅深度强化学习笔记(六)Imitation Learning
李宏毅深度强化学习- Imitation LearningWhy Imitation LearningBehaviour CloningInverse Reinforcement Learning (IRL)李宏毅深度强化学习课程 https://www.bilibili.com/video/av24724071李宏毅深度强化学习笔记(一)Outline李宏毅深度强化学习笔记(二)Pro...原创 2019-03-01 11:15:41 · 3552 阅读 · 0 评论 -
【笔记2-3】李宏毅深度强化学习笔记(三)Q-Learning
李宏毅深度强化学习- Q-LearningIntroduction of Q-LearningBasic ideasQ-Learning:Tips of Q-LearningQ-Learning for Continuous Actions李宏毅深度强化学习课程 https://www.bilibili.com/video/av24724071Introduction of Q-Learn...原创 2019-03-18 09:23:24 · 12547 阅读 · 9 评论 -
【笔记2-1】李宏毅深度强化学习笔记(一)Outline
李宏毅强化学习-1 IntroductionReinforcement learning:Examples:Properties of RL:RL ApproachPolicy-based approach -- learn an actorValue-based approach -- learn a criticActor-CriticReinforcement learning:What...原创 2019-02-24 17:40:14 · 14498 阅读 · 0 评论 -
【笔记2-2】李宏毅深度强化学习笔记(二)Proximal Policy Optimization (PPO)
李宏毅强化学习- Proximal Policy OptimizationPolicy GradientTerms and basic ideasPolicy Gradient:From on-policy to off-policy ——Using the experience more than onceTerms and basic ideasPPO algorithm:Policy Gr...原创 2019-02-24 19:12:09 · 35517 阅读 · 17 评论