RL的一些个人阅读笔记
持续整理……
由于是用typora写的,所以里面公式都是latex格式的,为了阅读方便我也传了pdf格式和html格式。
Towards a Unified Theory of State Abstraction for MDPs
Trust Region Policy Optimization
Statistical Reinforcement Learning - Note 1
deep_attention_recurrent_q_network
Abstraction Selection in Model-Based Reinforcement Learning Safe RL Meta RL 和Model-based RL