SMDP Homomorphisms: An Algebraic Approach to Abstraction in Semi-Markov Decision Processes.

Balaraman Ravindran Andrew G. Barto

Published in: IJCAI (2003)

Keyphrases

semi markov decision processes
markov decision processes
decision theoretic planning
average reward
optimal policy
state space
state abstraction
reinforcement learning
dynamic programming
decision processes