On the Practical Art of State Definitions for Markov Decision Process Construction.

William T. Scherer Stephen C. Adams Peter A. Beling

Published in: IEEE Access (2018)

Keyphrases

markov decision process
state space
optimal policy
reinforcement learning
markov decision processes
initial state
infinite horizon
finite horizon
state action
reinforcement learning algorithms
decision making
dynamic programming
probabilistic model
state variables
reward function