Cooperative control for multi-player pursuit-evasion games with reinforcement learning.
Yuanda WangLu DongChangyin SunPublished in: Neurocomputing (2020)
Keyphrases
- multi player
- pursuit evasion
- cooperative
- game playing
- online game
- reinforcement learning
- game play
- educational games
- multi agent
- optimal control
- game theory
- function approximation
- state space
- computer games
- incomplete information
- model free
- solution concepts
- multi agent systems
- learning algorithm
- game design
- reinforcement learning algorithms
- policy iteration
- temporal difference
- role playing game
- game theoretic