Effectiveness of Considering State Similarity for Reinforcement Learning.

Sertan Girgin Faruk Polat Reda Alhajj

Published in: IDEAL (2006)

Keyphrases

reinforcement learning
state space
learning algorithm
similarity measure
distance measure
similarity measurement
temporal difference learning
neural network
information retrieval
dynamic programming
optimal policy
learning problems
evaluation function
state action
state abstraction
transition model