Integral reinforcement learning-based dynamic event-triggered safety control for multiplayer Stackelberg-Nash games with time-varying state constraints.
Chunbin QinTianzeng ZhuKaijun JiangYinliang WuPublished in: Eng. Appl. Artif. Intell. (2024)
Keyphrases
- nash equilibria
- game theory
- nash equilibrium
- reinforcement learning
- dynamic constraints
- computer games
- state space
- control problems
- incomplete information
- online game
- game theoretic
- imperfect information
- dynamic environments
- leader follower
- game play
- machine learning
- optimal control
- control policy
- cooperative game
- multi agent
- control method
- event detection
- robot control
- function approximation
- traffic signal
- multiagent learning
- mixed strategy
- action selection
- game playing
- reinforcement learning agents
- formation control
- serious games