Safe Reinforcement Learning with Dual Robustness.
Zeyang LiChuxiong HuYunan WangYujie YangShengbo Eben LiPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- state space
- machine learning
- data sets
- reinforcement learning algorithms
- temporal difference
- multi agent
- function approximation
- supervised learning
- relational reinforcement learning
- real time
- high robustness
- optimal control
- markov decision processes
- least squares
- dynamic programming
- learning process
- case study
- website
- learning algorithm
- databases