Decentralized optimal large scale multi-player pursuit-evasion strategies: A mean field game approach with reinforcement learning.
Zejian ZhouHao XuPublished in: Neurocomputing (2022)
Keyphrases
- pursuit evasion
- multi player
- game playing
- reinforcement learning
- online game
- optimal strategy
- multi agent
- game play
- dynamic programming
- closed form
- optimal control
- educational games
- solution concepts
- cooperative
- video games
- function approximation
- markov random field
- reinforcement learning algorithms
- game design
- stochastic games
- game theory
- markov decision processes
- infinite horizon
- model free
- optimal policy
- worst case
- monte carlo
- nash equilibrium