On the Robustness of Safe Reinforcement Learning under Observational Perturbations.
Zuxin LiuZijian GuoZhepeng CenHuan ZhangJie TanBo LiDing ZhaoPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- learning algorithm
- robot control
- multi agent
- reinforcement learning algorithms
- hidden markov models
- model free
- optimal control
- policy search
- temporal difference
- learning problems
- supervised learning
- dynamic programming
- learning process
- training data
- high robustness
- machine learning