paper-with-me

Papers

Harnessing Density Ratios for Online Reinforcement Learning

2024-01-18 · Philip Amortila, Dylan J. Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie

The theories of offline and online reinforcement learning, despite having evolved in parallel, have begun to show signs of the possibility for a unification, with algorithms and analysis techniques for one setting often having natural counterparts in the other. However, the notion of density ratio modeling, an emerging paradigm in offline RL, has been largely absent from online RL, perhaps for good reason: the very existence and boundedness of density ratios relies on access to an exploratory dataset with good coverage, but the core challenge in online RL is to collect such a dataset without having one to start. In this work we show -- perhaps surprisingly -- that density ratio-based algorithms have online counterparts. Assuming only the existence of an exploratory distribution with good coverage, a structural condition known as coverability (Xie et al., 2023), we give a new algorithm (GLOW) that uses density ratio realizability and value function realizability to perform sample-efficient online exploration. GLOW addresses unbounded density ratios via careful use of truncation, and combines this with optimism to guide exploration. GLOW is computationally inefficient; we complement it with a more efficient counterpart, HyGLOW, for the Hybrid RL setting (Song et al., 2022) wherein online RL is augmented with additional offline data. HyGLOW is derived as a special case of a more general meta-algorithm that provides a provable black-box reduction from hybrid RL to offline RL, which may be of independent interest.

📄 PDF Abstract BibTeX arXiv:2401.09681

Code (0)

등록된 구현이 없습니다.

Tasks

Offline RLreinforcement-learningReinforcement Learning

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…
Invertible 1x1 Convolution The Invertible 1x1 Convolution is a type of convolution used in flow-based generative models that reverses the ordering of…
Affine Coupling 설명 없음
Activation Normalization Activation Normalization is a type of normalization used for flow-based generative models; specifically it was introduced in the GLOW
GLOW 설명 없음

Similar Papers 제목 키워드 기반

Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation

2020-01-01 · ICML 2020 1 · Nathan Kallus, Masatoshi Uehara

Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. We consider for the first time t…

Off-policy evaluationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes

2019-08-22 · Nathan Kallus, Masatoshi Uehara

Off-policy evaluation (OPE) in reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. We consider for the first time t…

Off-policy evaluationreinforcement-learningReinforcement LearningReinforcement Learning (RL)

AVG-DICE: Stationary Distribution Correction by Regression

2025-03-03 · Fengdi Che, Bryan Chan, Chen Ma, A. Rupam Mahmood

Off-policy policy evaluation (OPE), an essential component of reinforcement learning, has long suffered from stationary state distribution mismatch, undermining both stability and accuracy of OPE estimates. While existin…

AvgMuJoCoregression

Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets

2025-10-01 · Shriram Karpoora Sundara Pandian, Ali Baheri arxiv

Offline reinforcement learning (RL) enables policy optimization from fixed datasets, making it suitable for safety-critical applications where online exploration is infeasible. However, these datasets are often contamina…

Reinforcement LearningContinuous ControlOffline RL

GradientDICE: Rethinking Generalized Offline Estimation of Stationary Values

2020-01-29 · ICML 2020 1 · Shangtong Zhang, Bo Liu, Shimon Whiteson

We present GradientDICE for estimating the density ratio between the state distribution of the target policy and the sampling distribution in off-policy reinforcement learning. GradientDICE fixes several problems of GenD…

Reinforcement Learning