An adaptive strategy via reinforcement learning for the prisoner U+02BC s dilemma game.
Lei XueChangyin SunDonald WunschYingjiang ZhouFang YuPublished in: IEEE CAA J. Autom. Sinica (2018)
Keyphrases
- reinforcement learning
- optimal strategy
- two player games
- exploration exploitation dilemma
- function approximation
- game theory
- game ai
- reinforcement learning algorithms
- computer games
- video games
- educational games
- temporal difference
- game theoretic
- game playing
- search strategy
- learning problems
- state space
- game design
- machine learning
- evaluation function
- optimal policy
- game development
- temporal difference learning
- multi agent
- leader follower
- learning algorithm