A Distributed Reinforcement Learning Approach to Pattern Inference in Go.
Myriam AbramsonHarry WechslerPublished in: ICMLA (2003)
Keyphrases
- reinforcement learning
- multi agent
- distributed systems
- distributed environment
- cooperative
- learning algorithm
- bayesian networks
- function approximation
- lightweight
- peer to peer
- state space
- optimal policy
- reinforcement learning algorithms
- pattern matching
- markov decision processes
- temporal difference
- model free
- database
- inference process
- communication cost
- probabilistic inference
- computer networks
- mobile agents
- dynamic programming