Transient and asymptotic dynamics of reinforcement learning in games.
Luis R. IzquierdoSegismundo S. IzquierdoNicholas Mark GottsGary PolhillPublished in: Games Econ. Behav. (2007)
Keyphrases
- reinforcement learning
- action sets
- learning agents
- minority game
- steady state
- video games
- game theory
- game theoretic
- function approximation
- dynamic model
- computer games
- reinforcement learning agents
- dynamic programming
- markov decision processes
- multi agent
- asymptotically optimal
- model free
- multiagent learning
- game play
- machine learning
- learning algorithm
- cooperative
- state space
- optimal policy
- dynamical systems
- transfer learning
- action selection
- temporal difference
- worst case
- neural network
- incomplete information
- expected values
- evolutionary game theory
- learning process
- perfect information
- function approximators
- nash equilibria
- reinforcement learning algorithms
- multiagent systems
- game playing
- game design
- serious games
- educational games
- optimal control
- nash equilibrium
- decision problems