Temporal Regularization in Markov Decision Process.

Pierre Thodoroff Audrey Durand Joelle Pineau Doina Precup

Published in: CoRR (2018)

Keyphrases

markov decision process
state space
markov decision processes
reinforcement learning
optimal policy
finite horizon
temporal information
infinite horizon
transition matrices
transition probabilities
temporal difference learning
initial state
policy iteration
decision making
search space