Joint Synthesis of Safety Certificate and Safe Control Policy using Constrained Reinforcement Learning.
Haitong MaChangliu LiuShengbo Eben LiSifa ZhengJianyu ChenPublished in: CoRR (2021)
Keyphrases
- control policy
- reinforcement learning
- control policies
- approximate dynamic programming
- admission control
- long run
- function approximation
- traffic signal
- program synthesis
- multi agent
- state space
- batch mode
- model free
- learning algorithm
- temporal difference
- optimal policy
- texture synthesis
- reinforcement learning algorithms
- dynamic programming
- continuous state
- machine learning
- optimal control
- markov decision processes
- transfer learning
- mobile robot
- lower bound