Active Exploration in Markov Decision Processes.

Jean Tarbouriech Alessandro Lazaric

Published in: CoRR (2019)

Keyphrases

markov decision processes
active exploration
reinforcement learning
state space
finite state
optimal policy
active learning
problem based learning

policy iteration
reachability analysis
small sample
transition matrices
planning under uncertainty
partially observable
dynamic programming
decision theoretic planning

average cost
average reward
model based reinforcement learning
action space
state and action spaces
decision trees
reward function
infinite horizon

markov decision process
model free
game playing
least squares
optical flow
case study
machine learning