Bayesian Policy Search for Stochastic Domains.

David Tolpin Yuan Zhou Hongseok Yang

Published in: CoRR (2020)

Keyphrases

stochastic domains
policy search
partially observable markov decision processes
markov decision problems
reinforcement learning
state space
finite state
dynamic programming

linear programming
reinforcement learning algorithms
dynamical systems
planning problems
belief state
bayesian networks
optimal policy

markov decision processes
reward function
partially observable
decision problems
decision theoretic
multi agent
utility function

neural network
decision theory
infinite horizon
linear program
average cost
domain independent
decision processes