English
Related papers

Related papers: Projected Off-Policy Q-Learning (POP-QL) for Stabi…

200 papers

Offline Reinforcement Learning (RL) aims to learn policies from previously collected datasets without exploring the environment. Directly applying off-policy algorithms to offline RL usually fails due to the extrapolation error caused by…

Machine Learning · Computer Science 2022-02-24 Chenjia Bai , Lingxiao Wang , Zhuoran Yang , Zhihong Deng , Animesh Garg , Peng Liu , Zhaoran Wang

Off-policy reinforcement learning holds the promise of sample-efficient learning of decision-making policies by leveraging past experience. However, in the offline RL setting -- where a fixed collection of interactions are provided and no…

Machine Learning · Computer Science 2021-01-15 Seyed Kamyar Seyed Ghasemipour , Dale Schuurmans , Shixiang Shane Gu

The offline reinforcement learning (RL) paradigm provides a general recipe to convert static behavior datasets into policies that can perform better than the policy that collected the data. While policy constraints, conservatism, and other…

Artificial Intelligence · Computer Science 2023-10-19 Jianlan Luo , Perry Dong , Jeffrey Wu , Aviral Kumar , Xinyang Geng , Sergey Levine

Offline-to-online Reinforcement Learning (O2O RL) aims to improve the performance of offline pretrained policy using only a few online samples. Built on offline RL algorithms, most O2O methods focus on the balance between RL objective and…

Machine Learning · Computer Science 2023-12-14 Yinmin Zhang , Jie Liu , Chuming Li , Yazhe Niu , Yaodong Yang , Yu Liu , Wanli Ouyang

Off-policy learning ability is an important feature of reinforcement learning (RL) for practical applications. However, even one of the most elementary RL algorithms, temporal-difference (TD) learning, is known to suffer form divergence…

Machine Learning · Computer Science 2025-04-21 Han-Dong Lim , Donghwan Lee

Current Reinforcement Learning (RL) is often limited by the large amount of data needed to learn a successful policy. Offline RL aims to solve this issue by using transitions collected by a different behavior policy. We address a novel…

Machine Learning · Computer Science 2024-05-29 Johannes Ackermann , Takayuki Osa , Masashi Sugiyama

We address the problem of offline learning a policy that avoids undesirable demonstrations. Unlike conventional offline imitation learning approaches that aim to imitate expert or near-optimal demonstrations, our setting involves avoiding…

Machine Learning · Computer Science 2024-10-14 Huy Hoang , Tien Mai , Pradeep Varakantham

In this work, we consider the problem of model selection for deep reinforcement learning (RL) in real-world environments. Typically, the performance of deep RL algorithms is evaluated via on-policy interactions with the target environment.…

Machine Learning · Computer Science 2019-11-26 Alex Irpan , Kanishka Rao , Konstantinos Bousmalis , Chris Harris , Julian Ibarz , Sergey Levine

This paper investigates the problem of online prediction learning, where learning proceeds continuously as the agent interacts with an environment. The predictions made by the agent are contingent on a particular way of behaving,…

Machine Learning · Computer Science 2018-11-08 Sina Ghiassian , Andrew Patterson , Martha White , Richard S. Sutton , Adam White

In offline reinforcement learning, a policy is learned using a static dataset in the absence of costly feedback from the environment. In contrast to the online setting, only using static datasets poses additional challenges, such as…

Machine Learning · Computer Science 2025-12-16 Marvin Alles , Philip Becker-Ehmck , Patrick van der Smagt , Maximilian Karl

Reinforcement learning has emerged as a powerful tool for improving diffusion-based text-to-image models, but existing methods are largely limited to single-task optimization. Extending RL to multiple tasks is challenging: joint…

Machine Learning · Computer Science 2026-05-15 Quanhao Li , Junqiu Yu , Kaixun Jiang , Yujie Wei , Zhen Xing , Pandeng Li , Ruihang Chu , Shiwei Zhang , Yu Liu , Zuxuan Wu

Offline Reinforcement Learning promises to learn effective policies from previously-collected, static datasets without the need for exploration. However, existing Q-learning and actor-critic based off-policy RL algorithms fail when…

Machine Learning · Computer Science 2021-05-19 Yue Wu , Shuangfei Zhai , Nitish Srivastava , Joshua Susskind , Jian Zhang , Ruslan Salakhutdinov , Hanlin Goh

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

Off-policy learning exhibits greater instability when compared to on-policy learning in reinforcement learning (RL). The difference in probability distribution between the target policy ($\pi$) and the behavior policy (b) is a major cause…

Offline reinforcement learning (RL) enables data-efficient and safe policy learning without online exploration, but its performance often degrades under distribution shift. The learned policy may visit out-of-distribution state-action pairs…

Artificial Intelligence · Computer Science 2026-03-17 Hongqiang Lin , Zhenghui Fu , Weihao Tang , Pengfei Wang , Yiding Sun , Qixian Huang , Dongxu Zhang

Learning robust driving policies from large-scale, real-world datasets is a central challenge in autonomous driving, as online data collection is often unsafe and impractical. While Behavioral Cloning (BC) offers a straightforward approach…

Machine Learning · Computer Science 2025-08-28 Antonio Guillen-Perez

Offline reinforcement learning struggles with distributional shift and constrained performance due to static dataset limitations, while online RL demands prohibitive environment interactions. The recent advent of hybrid offline-to-online…

Machine Learning · Computer Science 2026-05-19 Qisai Liu , Zhanhong Jiang , Joshua Russell Waite , Aditya Balu , Cody Fleming , Soumik Sarkar

We study offline reinforcement learning of style-conditioned policies using explicit style supervision via subtrajectory labeling functions. In this setting, aligning style with high task performance is particularly challenging due to…

Machine Learning · Computer Science 2026-02-02 Mathieu Petitbois , Rémy Portelas , Sylvain Lamprier

One of the fundamental challenges for offline reinforcement learning (RL) is ensuring robustness to data distribution. Whether the data originates from a near-optimal policy or not, we anticipate that an algorithm should demonstrate its…

Machine Learning · Computer Science 2023-10-18 Xiaohan Hu , Yi Ma , Chenjun Xiao , Yan Zheng , Jianye Hao

Improving the performance of pre-trained policies through online reinforcement learning (RL) is a critical yet challenging topic. Existing online RL fine-tuning methods require continued training with offline pretrained Q-functions for…

Machine Learning · Computer Science 2025-05-23 Wei Xiao , Jiacheng Liu , Zifeng Zhuang , Runze Suo , Shangke Lyu , Donglin Wang