Measuring Structural Similarities in Finite MDPs.

Hao Wang Shaokang Dong Ling Shao

Published in: IJCAI (2019)

Keyphrases

structural similarities
state and action spaces
markov decision processes
state space
reinforcement learning
finite number
markov decision problems
optimal policy
action space
factored mdps
metadata
dynamic programming
knowledge representation
data quality
reward function