English
Related papers

Related papers: Off-Policy Self-Critical Training for Transformer …

200 papers

Offline reinforcement learning (RL) extends the paradigm of classical RL algorithms to purely learning from static datasets, without interacting with the underlying environment during the learning process. A key challenge of offline RL is…

Machine Learning · Computer Science 2022-06-16 Shentao Yang , Yihao Feng , Shujian Zhang , Mingyuan Zhou

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 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

Importance sampling (IS) is a common reweighting strategy for off-policy prediction in reinforcement learning. While it is consistent and unbiased, it can result in high variance updates to the weights for the value function. In this work,…

Machine Learning · Computer Science 2019-11-15 Matthew Schlegel , Wesley Chung , Daniel Graves , Jian Qian , Martha White

Off-policy deep reinforcement learning (RL) algorithms are incapable of learning solely from batch offline data without online interactions with the environment, due to the phenomenon known as \textit{extrapolation error}. This is often due…

Machine Learning · Computer Science 2019-12-03 Riashat Islam , Komal K. Teru , Deepak Sharma , Joelle Pineau

The past years have seen Large Language Models (LLMs) strive not only as generative models but also as agents solving textual sequential decision-making tasks. When facing complex environments where their zero-shot abilities are…

Machine Learning · Computer Science 2026-01-30 Loris Gaven , Clement Romac , Thomas Carta , Sylvain Lamprier , Olivier Sigaud , Pierre-Yves Oudeyer

Deploying reinforcement learning in the real world remains challenging due to sample inefficiency, sparse rewards, and noisy visual observations. Prior work leverages demonstrations and human feedback to improve learning efficiency and…

Artificial Intelligence · Computer Science 2026-01-23 Xiefeng Wu , Mingyu Hu , Shu Zhang

Offline reinforcement learning (RL) aims to find a near-optimal policy using pre-collected datasets. In real-world scenarios, data collection could be costly and risky; therefore, offline RL becomes particularly challenging when the…

Machine Learning · Computer Science 2024-12-18 Ruizhe Shi , Yuyao Liu , Yanjie Ze , Simon S. Du , Huazhe Xu

Large language models distill broad knowledge from text corpora. However, they can be inconsistent when it comes to completing user specified tasks. This issue can be addressed by finetuning such models via supervised learning on curated…

Computation and Language · Computer Science 2023-05-02 Charlie Snell , Ilya Kostrikov , Yi Su , Mengjiao Yang , Sergey Levine

Learning from multi-step off-policy data collected by a set of policies is a core problem of reinforcement learning (RL). Approaches based on importance sampling (IS) often suffer from large variances due to products of IS ratios. Typical…

Despite the remarkable success of Deep RL in learning control policies from raw pixels, the resulting models do not generalize. We demonstrate that a trained agent fails completely when facing small visual changes, and that…

Computer Vision and Pattern Recognition · Computer Science 2019-07-05 Shani Gamrian , Yoav Goldberg

Recommender systems (RecSys) have become critical tools for enhancing user engagement by delivering personalized content across diverse digital platforms. Recent advancements in large language models (LLMs) demonstrate significant potential…

Information Retrieval · Computer Science 2025-10-16 Yi Zhang , Lili Xie , Ruihong Qiu , Jiajun Liu , Sen Wang

Large language models (LLMs) excel in tasks like question answering and dialogue, but complex tasks requiring interaction, such as negotiation and persuasion, require additional long-horizon reasoning and planning. Reinforcement learning…

Computation and Language · Computer Science 2025-12-04 Joey Hong , Anca Dragan , Sergey Levine

Training Large Language Models (LLMs) to reason often relies on Reinforcement Learning (RL) with task-specific verifiers. However, many real-world reasoning-intensive tasks lack verifiers, despite offering abundant expert demonstrations…

Machine Learning · Computer Science 2025-12-10 Locke Cai , Ivan Provilkov

Offline reinforcement learning (RL) enables learning effective policies from fixed datasets without any environment interaction. Existing methods typically employ policy constraints to mitigate the distribution shift encountered during…

Machine Learning · Computer Science 2026-04-30 Tan Jing , Xiaorui Li , Chao Yao , Xiaojuan Ban , Yuetong Fang , Renjing Xu , Zhaolin Yuan

Offline reinforcement learning (RL) enables the agent to effectively learn from logged data, which significantly extends the applicability of RL algorithms in real-world scenarios where exploration can be expensive or unsafe. Previous works…

Machine Learning · Computer Science 2022-12-05 Yiqin Yang , Hao Hu , Wenzhe Li , Siyuan Li , Jun Yang , Qianchuan Zhao , Chongjie Zhang

The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap…

Computation and Language · Computer Science 2023-03-16 Govardana Sachithanandam Ramachandran , Kazuma Hashimoto , Caiming Xiong

Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes…

Machine Learning · Computer Science 2024-05-07 Stone Tao , Arth Shukla , Tse-kai Chan , Hao Su

The ability to discover optimal behaviour from fixed data sets has the potential to transfer the successes of reinforcement learning (RL) to domains where data collection is acutely problematic. In this offline setting, a key challenge is…

Machine Learning · Computer Science 2022-11-23 Alex Beeson , Giovanni Montana

Model-free deep reinforcement learning (RL) methods have been successful in a wide variety of simulated domains. However, a major obstacle facing deep RL in the real world is their high sample complexity. Batch policy gradient methods offer…

Machine Learning · Computer Science 2017-03-01 Shixiang Gu , Timothy Lillicrap , Zoubin Ghahramani , Richard E. Turner , Sergey Levine