Efficient PAC-Optimal Exploration in Concurrent, Continuous State MDPs with Delayed Updates.

Jason Pazis Ronald Parr

Published in: AAAI (2016)

Keyphrases

continuous state
reinforcement learning
continuous state spaces
dynamic programming
action space
continuous state and action spaces
optimal solution
state space
markov decision processes
policy search
finite horizon
control policies
computational complexity
heuristic search
action selection
state dependent