Min-Max Q-learning for multi-player pursuit-evasion games.
Jhanani SelvakumarEfstathios BakolasPublished in: Neurocomputing (2022)
Keyphrases
- min max
- multi player
- pursuit evasion
- game playing
- online game
- multi agent
- educational games
- reinforcement learning
- game play
- video games
- cooperative
- solution concepts
- learning algorithm
- function approximation
- stochastic games
- state space
- optimal policy
- reinforcement learning algorithms
- computer games
- role playing game
- model free
- action selection
- coalition formation
- game design
- temporal difference
- dynamic environments
- coalitional games
- decision problems
- game theory