Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning.
Haitong MaChangliu LiuShengbo Eben LiSifa ZhengJianyu ChenPublished in: L4DC (2022)
Keyphrases
- control policy
- reinforcement learning
- control policies
- approximate dynamic programming
- long run
- admission control
- function approximation
- batch mode
- traffic signal
- state space
- temporal difference
- action selection
- program synthesis
- continuous state
- machine learning
- reinforcement learning algorithms
- control strategies
- model free
- markov decision processes
- linear programming
- decision making