English
Related papers

Related papers: Off-Policy Learning with Limited Supply

200 papers

Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due to its inherent on-policy nature, its proficiency in harnessing data from disparate policies…

Machine Learning · Computer Science 2024-06-07 Yaozhong Gan , Renye Yan , Xiaoyang Tan , Zhe Wu , Junliang Xing

Motivated by practical needs of experimentation and policy learning in online platforms, we study the problem of safe data collection. Specifically, our goal is to develop a logging policy that efficiently explores different actions to…

Machine Learning · Computer Science 2022-08-08 Ruihao Zhu , Branislav Kveton

A key goal in stochastic contextual linear bandits is to efficiently learn a near-optimal policy. Prior algorithms for this problem learn a policy by strategically sampling actions but naively (passively) sampling contexts from the…

Machine Learning · Computer Science 2026-05-26 Emma Brunskill , Ishani Karmarkar , Zhaoqi Li

We study the problem of online learning in Stackelberg games with side information between a leader and a sequence of followers. In every round the leader observes contextual information and commits to a mixed strategy, after which the…

Machine Learning · Computer Science 2026-05-05 Maria-Florina Balcan , Martino Bernasconi , Matteo Castiglioni , Andrea Celli , Keegan Harris , Zhiwei Steven Wu

Offline goal-conditioned reinforcement learning (GCRL) aims at solving goal-reaching tasks with sparse rewards from an offline dataset. While prior work has demonstrated various approaches for agents to learn near-optimal policies, these…

Robotics · Computer Science 2024-03-05 Chenyang Cao , Zichen Yan , Renhao Lu , Junbo Tan , Xueqian Wang

We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and correctly incorporates techniques from importance…

Machine Learning · Computer Science 2012-10-19 Miroslav Dudik , Dumitru Erhan , John Langford , Lihong Li

We consider imitation learning problems where the learner's ability to mimic the expert increases throughout the course of an episode as more information is revealed. One example of this is when the expert has access to privileged…

Machine Learning · Computer Science 2023-01-18 Gokul Swamy , Sanjiban Choudhury , J. Andrew Bagnell , Zhiwei Steven Wu

Reinforcement learning (RL) using foundation models for policy approximations in multi-turn tasks remains challenging. We identify two main limitations related to sparse reward settings and policy gradient updates, based on which we…

Machine Learning · Computer Science 2025-11-14 Georgios Papoudakis , Thomas Coste , Jianye Hao , Jun Wang , Kun Shao

Offline preference optimization is a key method for enhancing and controlling the quality of Large Language Model (LLM) outputs. Typically, preference optimization is approached as an offline supervised learning task using manually-crafted…

Machine Learning · Computer Science 2024-11-05 Chris Lu , Samuel Holt , Claudio Fanconi , Alex J. Chan , Jakob Foerster , Mihaela van der Schaar , Robert Tjarko Lange

As Large Language Models (LLMs) continue to grow in both capability and cost, transferring frontier capabilities into smaller, deployable students has become a central engineering problem, and knowledge distillation remains the dominant…

Machine Learning · Computer Science 2026-05-19 Mingyang Song , Mao Zheng

Contextual bandits are canonical models for sequential decision-making under uncertainty in environments with time-varying components. In this setting, the expected reward of each bandit arm consists of the inner product of an unknown…

Machine Learning · Statistics 2022-05-27 Hongju Park , Mohamad Kazem Shirani Faradonbeh

Offline reinforcement learning provides a viable approach to obtain advanced control strategies for dynamical systems, in particular when direct interaction with the environment is not available. In this paper, we introduce a conceptual…

Machine Learning · Computer Science 2024-01-04 Marc Weber , Phillip Swazinna , Daniel Hein , Steffen Udluft , Volkmar Sterzing

In the framework of Markov Decision Processes, off-policy learning, that is the problem of learning a linear approximation of the value function of some fixed policy from one trajectory possibly generated by some other policy. We briefly…

Artificial Intelligence · Computer Science 2013-04-16 Matthieu Geist , Bruno Scherrer

We consider the contextual bandit problem on general action and context spaces, where the learner's rewards depend on their selected actions and an observable context. This generalizes the standard multi-armed bandit to the case where side…

Machine Learning · Statistics 2023-01-03 Moise Blanchard , Steve Hanneke , Patrick Jaillet

Context distillation enables language models to internalize in-context knowledge into their parameters. In our work, we propose On-Policy Context Distillation (OPCD), a framework that bridges on-policy distillation with context distillation…

Computation and Language · Computer Science 2026-03-24 Tianzhu Ye , Li Dong , Xun Wu , Shaohan Huang , Furu Wei

Offline Reinforcement Learning (RL) offers an attractive alternative to interactive data acquisition by leveraging pre-existing datasets. However, its effectiveness hinges on the quantity and quality of the data samples. This work explores…

Machine Learning · Computer Science 2024-10-17 Wen Zheng Terence Ng , Jianda Chen , Tianwei Zhang

A fundamental challenge in contextual bandits is to develop flexible, general-purpose algorithms with computational requirements no worse than classical supervised learning tasks such as classification and regression. Algorithms based on…

Machine Learning · Computer Science 2020-06-24 Dylan J. Foster , Alexander Rakhlin

Learning from Observations (LfO) is a practical reinforcement learning scenario from which many applications can benefit through the reuse of incomplete resources. Compared to conventional imitation learning (IL), LfO is more challenging…

Machine Learning · Computer Science 2021-03-01 Zhuangdi Zhu , Kaixiang Lin , Bo Dai , Jiayu Zhou

On-Policy Distillation (OPD) has gained wide attraction as an LLM post-training paradigm due to its effectiveness in improving capabilities without introducing model distribution drift, and consequently, regression in general tasks.…

Artificial Intelligence · Computer Science 2026-05-25 Aristotelis Lazaridis , Dylan Bates , Aman Sharma , Brian King , Vincent Lu , Jack FitzGerald

Training practical agents usually involve offline and online reinforcement learning (RL) to balance the policy's performance and interaction costs. In particular, online fine-tuning has become a commonly used method to correct the erroneous…

Machine Learning · Computer Science 2023-06-07 Qisen Yang , Shenzhi Wang , Matthieu Gaetan Lin , Shiji Song , Gao Huang