Improving Online POMDP Planning Algorithms with Decaying Q Value.

Qingya Wang Feng Liu Xuan Wang Bin Luo

Published in: ICTAI (2023)

Keyphrases

online algorithms
online learning
computational cost
orders of magnitude
reinforcement learning
lower bound
data mining
learning algorithm
knowledge base
search space
significant improvement
state space
optimization problems
heuristic search
partially observable markov decision processes
theoretical justification