Value Preserving State-Action Abstractions.

David Abel Nate Umbanhowar Khimya Khetarpal Dilip Arumugam Doina Precup Michael L. Littman

Published in: AISTATS (2020)

Keyphrases

state action
evaluation function
reinforcement learning
average reward
markov decision process
action space
stochastic games
state transitions
markov decision processes
belief state
feature selection
state space
real valued
function approximators