Focused Real-Time Dynamic Programming for MDPs: Squeezing More Out of a Heuristic.

Trey Smith Reid G. Simmons

Published in: AAAI (2006)

Keyphrases

real time dynamic programming
markov decision processes
state space
dynamic programming
markov decision problems
reinforcement learning
optimal solution
finite state
planning under uncertainty
search algorithm
lower bound
multistage
search strategies
partially observable
finite horizon
action space