A Structure-aware Online Learning Algorithm for Markov Decision Processes.

Arghyadip Roy Vivek S. Borkar Abhay Karandikar Prasanna Chaporkar

Published in: VALUETOOLS (2019)

Keyphrases

markov decision processes
learning algorithm
reinforcement learning
reinforcement learning algorithms
state space
optimal policy
finite state
transition matrices

policy iteration
risk sensitive
dynamic programming
planning under uncertainty
reachability analysis
factored mdps
infinite horizon
reward function

partially observable
action space
average reward
learning tasks
state abstraction
policy evaluation
decision processes
finite horizon

model based reinforcement learning
optimal solution
action sets
state and action spaces
decision theoretic planning
average cost
multistage