English
Related papers

Related papers: Mitigating Distribution Shift in Model-based Offli…

200 papers

Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward…

Machine Learning · Computer Science 2021-02-15 Ron Dorfman , Idan Shenfeld , Aviv Tamar

This paper investigates the so-called reward-balancing methods, a novel class of algorithms for solving discounted-return reinforcement learning (RL) problems. These methods consist of iteratively adjusting the reward function to transform…

Optimization and Control · Mathematics 2026-04-23 Simone Baroncini , Bahman Gharesifard , Giuseppe Notarstefano

Despite their impressive performance on a wide variety of tasks, modern language models remain susceptible to distribution shifts, exhibiting brittle behavior when evaluated on data that differs in distribution from their training data. In…

Machine Learning · Computer Science 2026-02-20 Victoria Lin , Louis-Philippe Morency , Eli Ben-Michael

Model-Free Reinforcement Learning has achieved meaningful results in stable environments but, to this day, it remains problematic in regime changing environments like financial markets. In contrast, model-based RL is able to capture some…

Machine Learning · Computer Science 2021-04-23 Eric Benhamou , David Saltiel , Serge Tabachnik , Sui Kai Wong , François Chareyron

Model-based offline reinforcement learning (RL) aims to enhance offline RL with a dynamics model that facilitates policy exploration. However, \textit{model exploitation} could occur due to inevitable model errors, degrading algorithm…

Machine Learning · Computer Science 2026-03-10 Zhongjian Qiao , Jiafei Lyu , Boxiang Lyu , Yao Shu , Siyang Gao , Shuang Qiu

Many real-world domains require safe decision making in uncertain environments. In this work, we introduce a deep reinforcement learning framework for approaching this important problem. We consider a distribution over transition models,…

Machine Learning · Computer Science 2023-10-27 James Queeney , Mouhacine Benosman

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

Alignment is vital for safely deploying large language models (LLMs). Existing techniques are either reward-based (training a reward model on preference pairs and optimizing with reinforcement learning) or reward-free (directly fine-tuning…

Computation and Language · Computer Science 2026-03-03 Ruoxi Cheng , Haoxuan Ma , Weixin Wang , Ranjie Duan , Jiexi Liu , Xiaoshuang Jia , Simeng Qin , Xiaochun Cao , Yang Liu , Xiaojun Jia

Reinforcement Learning is divided in two main paradigms: model-free and model-based. Each of these two paradigms has strengths and limitations, and has been successfully applied to real world domains that are appropriate to its…

Machine Learning · Computer Science 2017-10-19 Somil Bansal , Roberto Calandra , Kurtland Chua , Sergey Levine , Claire Tomlin

Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy by optimizing the…

Artificial Intelligence · Computer Science 2024-12-24 Songjun Tu , Jingbo Sun , Qichao Zhang , Yaocheng Zhang , Jia Liu , Ke Chen , Dongbin Zhao

Despite achieving excellent performance on benchmarks, deep neural networks often underperform in real-world deployment due to sensitivity to minor, often imperceptible shifts in input data, known as distributional shifts. These shifts are…

Machine Learning · Computer Science 2025-09-25 Birk Torpmann-Hagen , Pål Halvorsen , Michael A. Riegler , Dag Johansen

Prior work in multi-objective reinforcement learning typically uses linear reward scalarization with fixed weights, which provably fails to capture non-convex Pareto fronts and thus yields suboptimal results. This limitation becomes…

Machine Learning · Computer Science 2026-04-01 Yining Lu , Zilong Wang , Shiyang Li , Xin Liu , Changlong Yu , Qingyu Yin , Zhan Shi , Zixuan Zhang , Meng Jiang

We reinterpret and propose a framework for pricing path-dependent financial derivatives by estimating the full distribution of payoffs using Distributional Reinforcement Learning (DistRL). Unlike traditional methods that focus on expected…

Mathematical Finance · Quantitative Finance 2025-07-18 Ahmet Umur Özsoy

In offline reinforcement learning, value overestimation caused by out-of-distribution (OOD) actions significantly limits policy performance. Recently, diffusion models have been leveraged for their strong distribution-matching capabilities,…

Machine Learning · Computer Science 2025-11-13 Yunchang Ma , Tenglong Liu , Yixing Lan , Xin Yin , Changxin Zhang , Xinglong Zhang , Xin Xu

We consider a problem of learning the reward and policy from expert examples under unknown dynamics. Our proposed method builds on the framework of generative adversarial networks and introduces the empowerment-regularized maximum-entropy…

Machine Learning · Computer Science 2019-02-26 Ahmed H. Qureshi , Byron Boots , Michael C. Yip

Reinforcement learning (RL) is increasingly used to align large language models (LLMs). Off-policy methods offer greater implementation simplicity and data efficiency than on-policy techniques, but often result in suboptimal performance. In…

Machine Learning · Computer Science 2025-12-01 Charles Arnal , Gaëtan Narozniak , Vivien Cabannes , Yunhao Tang , Julia Kempe , Remi Munos

Offline reinforcement learning (RL) is an effective tool for real-world recommender systems with its capacity to model the dynamic interest of users and its interactive nature. Most existing offline RL recommender systems focus on…

Information Retrieval · Computer Science 2025-05-13 Yi Zhang , Ruihong Qiu , Jiajun Liu , Sen Wang

Empirical risk minimization often performs poorly when the distribution of the target domain differs from those of source domains. To address such potential distribution shifts, we develop an unsupervised domain adaptation approach that…

Machine Learning · Statistics 2025-03-25 Zhenyu Wang , Peter Bühlmann , Zijian Guo

Offline Meta Reinforcement Learning (OMRL) aims to learn transferable knowledge from offline datasets to enhance the learning process for new target tasks. Context-based Reinforcement Learning (RL) adopts a context encoder to expediently…

Machine Learning · Computer Science 2023-05-24 Chenyang Zhao , Zihao Zhou , Bin Liu

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine