Distributed Model-Free Optimal Control for Multiagent Pursuit-Evasion Differential Games.
Huaipin ZhangWei ZhaoHui GeXiangpeng XieDong YuePublished in: IEEE Trans. Netw. Sci. Eng. (2024)
Keyphrases
- optimal control
- model free
- reinforcement learning
- multi agent
- pursuit evasion
- risk sensitive
- policy iteration
- reinforcement learning algorithms
- impedance control
- control problems
- function approximation
- stochastic games
- dynamic programming
- feedback control
- temporal difference
- optimal control problems
- policy evaluation
- state space
- game theory
- single agent
- learning algorithm
- rl algorithms
- multiagent systems
- average reward
- control strategy
- multiple agents
- infinite horizon
- control law
- markov decision processes
- nash equilibria
- temporal difference learning
- transfer learning
- linear programming