English
Related papers

Related papers: Offline Behavior Distillation

200 papers

Offline Reinforcement Learning has attracted much interest in solving the application challenge for traditional reinforcement learning. Offline reinforcement learning uses previously-collected datasets to train agents without any…

Machine Learning · Computer Science 2022-09-28 Chen Zhao , Kai Xing Huang , Chun yuan

Policy-based methods have achieved remarkable success in solving challenging reinforcement learning problems. Among these methods, off-policy policy gradient methods are particularly important due to that they can benefit from off-policy…

Machine Learning · Computer Science 2024-05-07 Wenjia Meng , Qian Zheng , Long Yang , Yilong Yin , Gang Pan

It is desirable for policies to optimistically explore new states and behaviors during online reinforcement learning (RL) or fine-tuning, especially when prior offline data does not provide enough state coverage. However, exploration…

Machine Learning · Computer Science 2023-10-13 Max Sobol Mark , Archit Sharma , Fahim Tajwar , Rafael Rafailov , Sergey Levine , Chelsea Finn

Training agents via off-policy deep reinforcement learning (RL) requires a large memory, named replay memory, that stores past experiences used for learning. These experiences are sampled, uniformly or non-uniformly, to create the batches…

Machine Learning · Computer Science 2022-12-27 Bumgeun Park , Taeyoung Kim , Woohyeon Moon , Luiz Felipe Vecchietti , Dongsoo Har

On-policy distillation (OPD) leverages dense teacher rewards to enhance reasoning models. However, scaling OPD to long-horizon tasks exposes a critical flaw: as the student's generated prefix inevitably diverges from the teacher's thought…

Machine Learning · Computer Science 2026-05-29 Zhicheng Yang , Zhijiang Guo , Yifan Song , Minrui Xu , Yongxin Wang , Yiwei Wang , Xiaodan Liang , Jing Tang

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

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by…

Machine Learning · Computer Science 2026-04-14 Hao Wang , Guozhi Wang , Han Xiao , Yufeng Zhou , Yue Pan , Jichao Wang , Ke Xu , Yafei Wen , Xiaohu Ruan , Xiaoxin Chen , Honggang Qi

Traditional offline reinforcement learning (RL) methods predominantly operate in a batch-constrained setting. This confines the algorithms to a specific state-action distribution present in the dataset, reducing the effects of…

Machine Learning · Statistics 2025-07-16 Charles A. Hepburn , Yue Jin , Giovanni Montana

Offline reinforcement learning (RL) can be used to improve future performance by leveraging historical data. There exist many different algorithms for offline RL, and it is well recognized that these algorithms, and their hyperparameter…

Machine Learning · Computer Science 2023-01-18 Allen Nie , Yannis Flet-Berliac , Deon R. Jordan , William Steenbergen , Emma Brunskill

Offline-to-online reinforcement learning (O2O RL) aims to obtain a continually improving policy as it interacts with the environment, while ensuring the initial policy behaviour is satisficing. This satisficing behaviour is necessary for…

Robotics · Computer Science 2025-01-24 Bryan Chan , Anson Leung , James Bergstra

In offline model-based reinforcement learning (offline MBRL), we learn a dynamic model from historically collected data, and subsequently utilize the learned model and fixed datasets for policy learning, without further interacting with the…

Machine Learning · Computer Science 2022-10-13 Shentao Yang , Shujian Zhang , Yihao Feng , Mingyuan Zhou

In safety-critical domains where online data collection is infeasible, offline reinforcement learning (RL) offers an attractive alternative but only if policies deliver high returns without incurring catastrophic lower-tail risk. Prior work…

Machine Learning · Computer Science 2025-12-09 Kai Fukazawa , Kunal Mundada , Iman Soltani

Model-based algorithms, which learn a dynamics model from logged experience and perform some sort of pessimistic planning under the learned model, have emerged as a promising paradigm for offline reinforcement learning (offline RL).…

Machine Learning · Computer Science 2022-01-28 Tianhe Yu , Aviral Kumar , Rafael Rafailov , Aravind Rajeswaran , Sergey Levine , Chelsea Finn

Offline reinforcement learning (RL), which aims to learn an optimal policy using a previously collected static dataset, is an important paradigm of RL. Standard RL methods often perform poorly in this regime due to the function…

Machine Learning · Computer Science 2023-08-29 Zhendong Wang , Jonathan J Hunt , Mingyuan Zhou

Recent advances in deep learning have shown significant potential for solving combinatorial optimization problems in real-time. Unlike traditional methods, deep learning can generate high-quality solutions efficiently, which is crucial for…

Machine Learning · Computer Science 2025-04-08 Imanol Echeverria , Maialen Murua , Roberto Santana

Most of the existing deep reinforcement learning (RL) approaches for session-based recommendations either rely on costly online interactions with real users, or rely on potentially biased rule-based or data-driven user-behavior models for…

Machine Learning · Computer Science 2020-12-17 Diksha Garg , Priyanka Gupta , Pankaj Malhotra , Lovekesh Vig , Gautam Shroff

We study the offline reinforcement learning (RL) in the face of unmeasured confounders. Due to the lack of online interaction with the environment, offline RL is facing the following two significant challenges: (i) the agent may be…

Machine Learning · Computer Science 2022-09-20 Zuyue Fu , Zhengling Qi , Zhaoran Wang , Zhuoran Yang , Yanxun Xu , Michael R. Kosorok

Offline reinforcement learning (RL) offers a promising direction for learning policies from pre-collected datasets without requiring further interactions with the environment. However, existing methods struggle to handle out-of-distribution…

Machine Learning · Computer Science 2024-03-12 Zhepeng Cen , Zuxin Liu , Zitong Wang , Yihang Yao , Henry Lam , Ding Zhao

Policy constraint methods to offline reinforcement learning (RL) typically utilize parameterization or regularization that constrains the policy to perform actions within the support set of the behavior policy. The elaborative designs of…

Machine Learning · Computer Science 2022-10-13 Jialong Wu , Haixu Wu , Zihan Qiu , Jianmin Wang , Mingsheng Long

On-Policy Distillation (OPD) has emerged as a dominant post-training paradigm for large language models, especially for reasoning domains. However, OPD remains unstable in practice due to the high gradient variance of its single-sample…

Machine Learning · Computer Science 2026-05-11 Minjae Oh , Sangjun Song , Gyubin Choi , Yunho Choi , Yohan Jo