Related papers: Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs

Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs

URL: http://arxiv.org/abs/2303.10859v1
Date: Mon, 20 Mar 2023 04:39:39 GMT
Title: Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs
Authors: Yuan Cheng, Ruiquan Huang, Jing Yang, Yingbin Liang
Abstract summary: This paper focuses on reward-free reinforcement learning under low-rank MDP models. We first provide the first known sample complexity lower bound for any algorithm under low-rank MDPs. We then propose a novel model-based algorithm, coined RAFFLE, and show it can both find an $epsilon$-optimal policy and achieve an $epsilon$-accurate system identification.
Score: 43.53286390357673
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In reward-free reinforcement learning (RL), an agent explores the environment first without any reward information, in order to achieve certain learning goals afterwards for any given reward. In this paper we focus on reward-free RL under low-rank MDP models, in which both the representation and linear weight vectors are unknown. Although various algorithms have been proposed for reward-free low-rank MDPs, the corresponding sample complexity is still far from being satisfactory. In this work, we first provide the first known sample complexity lower bound that holds for any algorithm under low-rank MDPs. This lower bound implies it is strictly harder to find a near-optimal policy under low-rank MDPs than under linear MDPs. We then propose a novel model-based algorithm, coined RAFFLE, and show it can both find an $\epsilon$-optimal policy and achieve an $\epsilon$-accurate system identification via reward-free exploration, with a sample complexity significantly improving the previous results. Such a sample complexity matches our lower bound in the dependence on $\epsilon$, as well as on $K$ in the large $d$ regime, where $d$ and $K$ respectively denote the representation dimension and action space cardinality. Finally, we provide a planning algorithm (without further interaction with true environment) for RAFFLE to learn a near-accurate representation, which is the first known representation learning guarantee under the same setting.