Adaptive Discretization using Voronoi Trees for Continuous-Action POMDPs.

Marcus Hörger Hanna Kurniawati Dirk P. Kroese Nan Ye

Published in: CoRR (2022)

Keyphrases

continuous action
partially observable markov decision processes
continuous state
policy search
reinforcement learning
finite state
dynamic programming
neural network
computational complexity
markov decision processes
action space
dynamical systems
control policies