Sample-Efficient Reinforcement Learning of Undercomplete POMDPs.

Chi Jin Sham M. Kakade Akshay Krishnamurthy Qinghua Liu

Published in: CoRR (2020)

Keyphrases

reinforcement learning
function approximation
markov decision processes
dynamic programming
state space
partially observable markov decision processes
computationally expensive
partially observable
continuous state
policy search