Towards Safe Reinforcement Learning via Constraining Conditional Value-at-Risk.
Chengyang YingXinning ZhouHang SuDong YanNing ChenJun ZhuPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- model free
- learning algorithm
- multi agent reinforcement learning
- control problems
- reinforcement learning algorithms
- robotic control
- reinforcement learning methods
- state space
- temporal difference
- direct policy search
- temporal difference learning
- function approximators
- optimal policy
- search algorithm
- optimal control
- radial basis function
- learning problems
- markov decision process
- action space
- supervised learning
- multi agent
- stochastic approximation
- bayesian networks
- knowledge base
- data sets