paper-with-me

Papers

Regularized Q-learning through Robust Averaging

2024-05-03 · Peter Schmitt-Förster, Tobias Sutter

We propose a new Q-learning variant, called 2RA Q-learning, that addresses some weaknesses of existing Q-learning methods in a principled manner. One such weakness is an underlying estimation bias which cannot be controlled and often results in poor performance. We propose a distributionally robust estimator for the maximum expected value term, which allows us to precisely control the level of estimation bias introduced. The distributionally robust estimator admits a closed-form solution such that the proposed algorithm has a computational cost per iteration comparable to Watkins' Q-learning. For the tabular case, we show that 2RA Q-learning converges to the optimal policy and analyze its asymptotic mean-squared error. Lastly, we conduct numerical experiments for various settings, which corroborate our theoretical findings and indicate that 2RA Q-learning often performs better than existing methods.

📄 PDF Abstract BibTeX arXiv:2405.02201

Code (1)

2raq/code 공식 구현

Tasks

Q-Learning

Methods 이 논문이 사용한 방법론

Q-Learning Q-Learning is an off-policy temporal difference control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} +…

Similar Papers 제목 키워드 기반

Optimal Regularized Dual Averaging Methods for Stochastic Optimization

2012-12-01 · NeurIPS 2012 12 · Xi Chen, Qihang Lin, Javier Pena

This paper considers a wide spectrum of regularized stochastic optimization problems where both the loss function and regularizer can be non-smooth. We develop a novel algorithm based on the regularized dual averaging (…

Stochastic Optimization

Granular feedback merits sophisticated aggregation

2025-07-16 · Anmol Kagrecha, Henrik Marklund, Potsawee Manakul, Richard Zeckhauser 외 arxiv

Human feedback is increasingly used across diverse applications like training AI models, developing recommender systems, and measuring public opinion -- with granular feedback often being preferred over binary feedback f…

Complementing reinforcement learning with SFT through logit averaging in the post training of LLMs

2026-05-19 · Xingwei Gan, Ying Zhu arxiv

We introduce a novel method that averages the logits of a frozen reference policy (e.g., SFT) and a trainable policy, and incorporate the method into Group Relative Policy Optimization (GRPO). In contrast to Reinforcemen…

Reinforcement Learning

Nested Model Averaging on Solution Path for High-dimensional Linear Regression

2020-05-16 · Yang Feng, Qing-Feng Liu

We study the nested model averaging method on the solution path for a high-dimensional linear regression problem. In particular, we propose to combine model averaging with regularized estimators (e.g., lasso and SLOPE) o…

regressionVocal Bursts Intensity Prediction

Dual Averaging Method for Regularized Stochastic Learning and Online Optimization

2009-12-01 · NeurIPS 2009 12 · Lin Xiao

We consider regularized stochastic learning and online optimization problems, where the objective function is the sum of two convex terms: one is the loss function of the learning task, and the other is a simple regulari…