Bellman Eluder Dimension: New Rich Classes of RL Problems, and Sample-Efficient Algorithms.

Chi Jin Qinghua Liu Sobhan Miryoosefi

Published in: CoRR (2021)

Keyphrases

np complete
optimization problems
reinforcement learning
solving problems
genetic algorithm
multi agent
state space
decision problems
function approximation
piecewise linear
problems involving
tractable cases