Approximability of Constant-horizon Constrained POMDP.

Majid Khonji Ashkan Jasour Brian C. Williams

Published in: IJCAI (2019)

Keyphrases

dynamical systems
reinforcement learning
optimal policy
partially observable
approximation algorithms
hidden state
finite state
partially observable markov decision processes
search space
special case
state space
belief state
model free reinforcement learning