paper-with-me

홈 › Papers

Value-aware Importance Weighting for Off-policy Reinforcement Learning

2023-06-27 · Kristopher De Asis, Eric Graves, Richard S. Sutton

Importance sampling is a central idea underlying off-policy prediction in reinforcement learning. It provides a strategy for re-weighting samples from a distribution to obtain unbiased estimates under another distribution. However, importance sampling weights tend to exhibit extreme variance, often leading to stability issues in practice. In this work, we consider a broader class of importance weights to correct samples in off-policy learning. We propose the use of $\textit{value-aware importance weights}$ which take into account the sample space to provide lower variance, but still unbiased, estimates under a target distribution. We derive how such weights can be computed, and detail key properties of the resulting importance weights. We then extend several reinforcement learning prediction algorithms to the off-policy setting with these weights, and evaluate them empirically.

📄 PDF Abstract BibTeX arXiv:2306.15625

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learningReinforcement Learning

Similar Papers 제목 키워드 기반

Importance Resampling for Off-policy Prediction

2019-06-11 · NeurIPS 2019 12 · Matthew Schlegel, Wesley Chung, Daniel Graves, Jian Qian 외

Importance sampling (IS) is a common reweighting strategy for off-policy prediction in reinforcement learning. While it is consistent and unbiased, it can result in high variance updates to the weights for the value func…

PredictionReinforcement Learning

Importance Resampling for Off-policy Policy Evaluation

2018-09-27 · Matthew Schlegel, Wesley Chung, Daniel Graves, Martha White

Importance sampling is a common approach to off-policy learning in reinforcement learning. While it is consistent and unbiased, it can result in high variance updates to the parameters for the value function. Weighted i…

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts

2026-01-15 · Sijia Luo, Xiaokang Zhang, Yuxuan Hu, Bohan Zhang 외 arxiv

Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing Key-Value (KV) caches during long-horizon…

Reinforcement Learning

Weighted importance sampling for off-policy learning with linear function approximation

2014-12-01 · NeurIPS 2014 12 · A. Rupam Mahmood, Hado P. Van Hasselt, Richard S. Sutton

Importance sampling is an essential component of off-policy model-free reinforcement learning algorithms. However, its most effective variant, \emph{weighted} importance sampling, does not carry over easily to function a…

Reinforcement Learning

MAD for Robust Reinforcement Learning in Machine Translation

2022-07-18 · Domenic Donato, Lei Yu, Wang Ling, Chris Dyer

We introduce a new distributed policy gradient algorithm and show that it outperforms existing reward-aware training procedures such as REINFORCE, minimum risk training (MRT) and proximal policy optimization (PPO) in ter…

Machine Translationreinforcement-learningReinforcement LearningReinforcement Learning (RL)+2