On verifying game designs and playing strategies using reinforcement learning.
Dimitrios KallesPanagiotis KanellopoulosPublished in: SAC (2001)
Keyphrases
- reinforcement learning
- game playing
- computer games
- human players
- temporal difference learning
- minimax search
- optimal strategy
- imperfect information
- card game
- two player games
- game players
- video games
- online game
- function approximation
- board game
- game theoretic
- games played
- game theory
- multi player
- educational games
- pac man
- evaluation function
- computer poker
- multi agent reinforcement learning
- multi agent
- design space
- reinforcement learning algorithms
- card games
- cooperative
- reinforcement learning agents
- learning process
- exploration strategy
- mixed strategy
- learning algorithm
- resource allocation
- state space
- game design
- model checking
- human computation
- markov decision processes
- repeated games
- stochastic games
- temporal difference
- serious games
- game play