Effects of ensemble action selection with different usage of player's memory resource on the evolution of cooperative strategies for iterated prisoner's dilemma game.
Takahiko SudoKazushi GotoYusuke NojimaHisao IshibuchiPublished in: CEC (2015)
Keyphrases
- action selection
- repeated games
- cooperative
- two player games
- game theory
- human players
- game play
- evolutionary game theory
- robot soccer
- minimax search
- basal ganglia
- evaluation function
- reinforcement learning
- optimal strategy
- incomplete information
- game theoretic
- imperfect information
- multi player
- temporal difference
- stochastic games
- decision making
- game players
- computer games
- game playing
- nash equilibrium
- ensemble methods
- action selection mechanism
- human robot
- boolean games
- card game
- computer poker
- pure nash equilibria
- solution concepts
- neural network
- game mechanics
- resource allocation
- massively multiplayer online role playing games
- game design
- mixed strategy
- video games
- board game
- multi agent
- average reward
- resource consumption
- artificial life
- multi agent systems
- learning algorithm
- human brain
- markov decision processes
- continuous state and action spaces