Temporal difference learning with eligibility traces for the game connect four.
Markus ThillSamineh BagheriPatrick KochWolfgang KonenPublished in: CIG (2014)
Keyphrases
- temporal difference learning
- eligibility traces
- reinforcement learning algorithms
- reinforcement learning
- game playing
- temporal difference
- state space
- function approximation
- model free
- markov decision processes
- reinforcement learning methods
- video games
- computer games
- learning algorithm
- educational games
- serious games
- fixed point
- game play
- reward function
- dynamic programming
- markov decision process
- multi agent