The Significance of Temporal-Difference Learning in Self-Play Training TD-Rummy versus EVO-rummy.
Clifford KotnikJugal K. KalitaPublished in: ICML (2003)
Keyphrases
- temporal difference learning
- game playing
- function approximation
- fixed point
- temporal difference
- evaluation function
- reinforcement learning
- approximate value iteration
- reinforcement learning algorithms
- training set
- gaussian process
- markov decision process
- video games
- belief propagation
- state space
- cost function
- function approximators
- decision making
- neural network