We study time-inhomogeneous episodic reinforcement learning (RL) under general function approximation and sparse rewards. We design a new algorithm, Variance-weighted Optimistic Q-Learning (VOQL), based on Q-learning and bound its regret assuming completeness and bounded Eluder dimension for the regression function class. As a special case, VOQL achieves O~(dHT+d6H5) regret over T episodes for a horizon H MDP under (d-dimensional) linear function approximation, which is asymptotically optimal. Our algorithm incorporates weighted regression-based upper and lower bounds on the optimal value function to obtain this improved regret. The algorithm is computationally efficient given a regression oracle over the function class, making this the first computationally tractable and statistically optimal approach for linear MDPs.
@article{arxiv.2212.06069,
title = {VO$Q$L: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation},
author = {Alekh Agarwal and Yujia Jin and Tong Zhang},
journal= {arXiv preprint arXiv:2212.06069},
year = {2022}
}