Reinforcement Learning with N-tuples on the Game Connect-4.
Markus ThillPatrick KochWolfgang KonenPublished in: PPSN (1) (2012)
Keyphrases
- reinforcement learning
- database
- computer games
- game playing
- function approximation
- game play
- game design
- game theory
- video games
- multi agent
- nash equilibrium
- model free
- learning algorithm
- temporal difference learning
- optimal policy
- state space
- role playing
- educational games
- optimal strategy
- reinforcement learning algorithms
- real time strategy games
- state abstraction
- two player games
- robotic control
- monte carlo tree search
- reinforcement learning methods
- serious games
- nash equilibria
- online game
- game based learning
- optimal control
- learning problems
- virtual world
- neural network
- data sets