Login / Signup
POMCPOW: An online algorithm for POMDPs with continuous state, action, and observation spaces.
Zachary Sunberg
Mykel J. Kochenderfer
Published in:
CoRR (2017)
Keyphrases
</>
dynamic programming
learning algorithm
belief state
machine learning
objective function
optimal solution
search space
np hard
convergence rate
reinforcement learning
search algorithm
computational complexity
state space
worst case
action space
average reward