English
Related papers

Related papers: Scaling Life-long Off-policy Learning

200 papers

Group Relative Policy Optimization (GRPO) has been a key driver of recent progress in reinforcement learning with verifiable rewards (RLVR) for large language models, but it is typically trained in a low-staleness, near-on-policy regime…

Machine Learning · Computer Science 2026-05-19 Minghao Tian , Yunfei Xie , Chen Wei

Reinforcement Learning (RL) can effectively learn complex policies. However, learning these policies often demands extensive trial-and-error interactions with the environment. In many real-world scenarios, this approach is not practical due…

Machine Learning · Computer Science 2024-02-19 Linh Le Pham Van , Hung The Tran , Sunil Gupta

In this work, we propose a computationally efficient algorithm for visual policy learning that leverages differentiable simulation and first-order analytical policy gradients. Our approach decouple the rendering process from the computation…

Machine Learning · Computer Science 2025-11-12 Haoxiang You , Yilang Liu , Ian Abraham

Generalizing policies across different domains with dynamics mismatch poses a significant challenge in reinforcement learning. For example, a robot learns the policy in a simulator, but when it is deployed in the real world, the dynamics of…

Machine Learning · Computer Science 2023-10-16 Kang Xu , Chenjia Bai , Xiaoteng Ma , Dong Wang , Bin Zhao , Zhen Wang , Xuelong Li , Wei Li

Reinforcement learning using a novel predictive representation is applied to autonomous driving to accomplish the task of driving between lane markings where substantial benefits in performance and generalization are observed on unseen test…

Machine Learning · Computer Science 2020-06-29 Daniel Graves , Nhat M. Nguyen , Kimia Hassanzadeh , Jun Jin

In principle, reinforcement learning and policy search methods can enable robots to learn highly complex and general skills that may allow them to function amid the complexity and diversity of the real world. However, training a policy that…

Machine Learning · Computer Science 2019-05-29 Ali Yahya , Adrian Li , Mrinal Kalakrishnan , Yevgen Chebotar , Sergey Levine

We propose world value functions (WVFs), a type of goal-oriented general value function that represents how to solve not just a given task, but any other goal-reaching task in an agent's environment. This is achieved by equipping an agent…

Artificial Intelligence · Computer Science 2022-06-27 Geraud Nangue Tasse , Benjamin Rosman , Steven James

Large, general-purpose robotic policies trained on diverse demonstration datasets have been shown to be remarkably effective both for controlling a variety of robots in a range of different scenes, and for acquiring broad repertoires of…

Robotics · Computer Science 2025-02-26 Mitsuhiko Nakamoto , Oier Mees , Aviral Kumar , Sergey Levine

Learning algorithms are enabling robots to solve increasingly challenging real-world tasks. These approaches often rely on demonstrations and reproduce the behavior shown. Unexpected changes in the environment may require using different…

Machine Learning · Computer Science 2020-02-19 Marija Jegorova , Stéphane Doncieux , Timothy Hospedales

Off-policy learning from multistep returns is crucial for sample-efficient reinforcement learning, particularly in the experience replay setting now commonly used with deep neural networks. Classically, off-policy estimation bias is…

Machine Learning · Computer Science 2021-12-24 Brett Daley , Christopher Amato

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techniques to prove asymptotic convergence, and to the best of our…

Machine Learning · Computer Science 2020-07-06 Bo Liu , Ji Liu , Mohammad Ghavamzadeh , Sridhar Mahadevan , Marek Petrik

This paper presents an off-policy Gaussian Predictive Control (GPC) framework aimed at solving optimal control problems with a smaller computational footprint, thereby facilitating real-time applicability while ensuring critical safety…

Robotics · Computer Science 2026-03-19 Shiva Kumar Tekumatla , Varun Gampa , Siavash Farzan

A long-standing challenge in artificial intelligence is lifelong reinforcement learning, where learners are given many tasks in sequence and must transfer knowledge between tasks while avoiding catastrophic forgetting. Policy reuse and…

Machine Learning · Computer Science 2023-11-07 David M. Bossens , Adam J. Sobey

Transfer Learning (TL) is a powerful tool that enables robots to transfer learned policies across different environments, tasks, or embodiments. To further facilitate this process, efforts have been made to combine it with Learning from…

Robotics · Computer Science 2025-03-18 Muhan Hou , Koen Hindriks , A. E. Eiben , Kim Baraka

Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunately, it has been challenging to combine off-policy learning…

Machine Learning · Computer Science 2019-01-04 Ahmed Touati , Pierre-Luc Bacon , Doina Precup , Pascal Vincent

Lifelong learning can be viewed as a continuous transfer learning procedure over consecutive tasks, where learning a given task depends on accumulated knowledge --- the so-called knowledge base. Most published work on lifelong learning…

Machine Learning · Statistics 2018-10-30 Changjian Shui , Ihsen Hedhli , Christian Gagné

Algorithmic decision-making in practice must be fair for legal, ethical, and societal reasons. To achieve this, prior research has contributed various approaches that ensure fairness in machine learning predictions, while comparatively…

Machine Learning · Computer Science 2023-10-10 Dennis Frauen , Valentyn Melnychuk , Stefan Feuerriegel

A longstanding goal in safe reinforcement learning (RL) is a method to ensure the safety of a policy throughout the entire process, from learning to operation. However, existing safe RL paradigms inherently struggle to achieve this…

Machine Learning · Computer Science 2025-05-29 Akifumi Wachi , Kohei Miyaguchi , Takumi Tanabe , Rei Sato , Youhei Akimoto

Pretrained on large-scale and diverse datasets, VLA models demonstrate strong generalization and adaptability as general-purpose robotic policies. However, Supervised Fine-Tuning (SFT), which serves as the primary mechanism for adapting…

Robotics · Computer Science 2026-05-19 Yuan Liu , Haoran Li , Shuai Tian , Yuxing Qin , Yuhui Chen , Yupeng Zheng , Yongzhen Huang , Dongbin Zhao

We study reinforcement learning for global decision-making in the presence of local agents, where the global decision-maker makes decisions affecting all local agents, and the objective is to learn a policy that maximizes the joint rewards…

Machine Learning · Computer Science 2024-10-24 Emile Anand , Guannan Qu