paper-with-me

홈 › Papers

Settling the Horizon-Dependence of Sample Complexity in Reinforcement Learning

2021-11-01 · Yuanzhi Li, Ruosong Wang, Lin F. Yang

Recently there is a surge of interest in understanding the horizon-dependence of the sample complexity in reinforcement learning (RL). Notably, for an RL environment with horizon length $H$, previous work have shown that there is a probably approximately correct (PAC) algorithm that learns an $O(1)$-optimal policy using $\mathrm{polylog}(H)$ episodes of environment interactions when the number of states and actions is fixed. It is yet unknown whether the $\mathrm{polylog}(H)$ dependence is necessary or not. In this work, we resolve this question by developing an algorithm that achieves the same PAC guarantee while using only $O(1)$ episodes of environment interactions, completely settling the horizon-dependence of the sample complexity in RL. We achieve this bound by (i) establishing a connection between value functions in discounted and finite-horizon Markov decision processes (MDPs) and (ii) a novel perturbation analysis in MDPs. We believe our new techniques are of independent interest and could be applied in related questions in RL.

📄 PDF Abstract BibTeX arXiv:2111.00633

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning

2025-11-29 · Na Li, Yuchen Jiao, Hangguan Shan, Shefeng Yan arxiv

The thriving field of multi-agent reinforcement learning (MARL) studies how a group of interacting agents make decisions autonomously in a shared dynamic environment. Existing theoretical studies in this area suffer from…

Multi-agent Reinforcement Learning

Settling the Sample Complexity of Model-Based Offline Reinforcement Learning

2022-04-11 · Gen Li, Laixi Shi, Yuxin Chen, Yuejie Chi 외

This paper is concerned with offline reinforcement learning (RL), which learns using pre-collected data without further exploration. Effective offline RL would be able to accommodate distribution shift and limited data c…

Offline RLreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Is Long Horizon Reinforcement Learning More Difficult Than Short Horizon Reinforcement Learning?

2020-05-01 · Ruosong Wang, Simon S. Du, Lin F. Yang, Sham M. Kakade

Learning to plan for long horizons is a central challenge in episodic reinforcement learning problems. A fundamental question is to understand how the difficulty of the problem scales as the horizon increases. Here the n…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Is Long Horizon RL More Difficult Than Short Horizon RL?

2020-12-01 · NeurIPS 2020 12 · Ruosong Wang, Simon S. Du, Lin Yang, Sham Kakade

Learning to plan for long horizons is a central challenge in episodic reinforcement learning problems. A fundamental question is to understand how the difficulty of the problem scales as the horizon increases. Here the n…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Optimal Sample Complexity of Reinforcement Learning for Mixing Discounted Markov Decision Processes

2023-02-15 · Shengbo Wang, Jose Blanchet, Peter Glynn

We consider the optimal sample complexity theory of tabular reinforcement learning (RL) for maximizing the infinite horizon discounted reward in a Markov decision process (MDP). Optimal worst-case complexity results have…

reinforcement-learningReinforcement Learning (RL)