Provably Efficient Reinforcement Learning with Aggregated States
Machine Learning
2020-02-20 v2 Machine Learning
Optimization and Control
Abstract
We establish that an optimistic variant of Q-learning applied to a fixed-horizon episodic Markov decision process with an aggregated state representation incurs regret , where is the horizon, is the number of aggregate states, is the number of episodes, and is the largest difference between any pair of optimal state-action values associated with a common aggregate state. Notably, this regret bound does not depend on the number of states or actions and indicates that asymptotic per-period regret is no greater than , independent of horizon. To our knowledge, this is the first such result that applies to reinforcement learning with nontrivial value function approximation without any restrictions on transition probabilities.
Cite
@article{arxiv.1912.06366,
title = {Provably Efficient Reinforcement Learning with Aggregated States},
author = {Shi Dong and Benjamin Van Roy and Zhengyuan Zhou},
journal= {arXiv preprint arXiv:1912.06366},
year = {2020}
}