Distributed Optimal Pursuit-Evasion Strategy of Multiple-Pursuer Single-Evader Game via Reinforcement Learning.
Jinrui ZhangHuaipin ZhangWei ZhaoPublished in: IECON (2023)
Keyphrases
- pursuit evasion
- reinforcement learning
- multiple independent
- optimal strategy
- optimal control
- multi agent
- dynamic programming
- distributed systems
- distributed environment
- multiple targets
- genetic algorithm
- state space
- markov decision processes
- cooperative multi agent systems
- control policy
- reinforcement learning algorithms
- action selection
- function approximation
- peer to peer
- cooperative