English
Related papers

Related papers: Coupled Local and Global World Models for Efficien…

200 papers

Despite extreme sample inefficiency, on-policy reinforcement learning, aka policy gradients, has become a fundamental tool in decision-making problems. With the recent advances in GPU-driven simulation, the ability to collect large amounts…

Machine Learning · Computer Science 2024-07-30 Jayesh Singla , Ananye Agarwal , Deepak Pathak

Online reinforcement learning (RL) methods are often data-inefficient or unreliable, making them difficult to train on real robotic hardware, especially quadruped robots. Learning robotic tasks from pre-collected data is a promising…

Robotics · Computer Science 2024-10-28 Hongyin Zhang , Shuyu Yang , Donglin Wang

We propose a novel formulation of robotic pick and place as a deep reinforcement learning (RL) problem. Whereas most deep RL approaches to robotic manipulation frame the problem in terms of low level states and actions, we propose a more…

Robotics · Computer Science 2018-02-26 Marcus Gualtieri , Andreas ten Pas , Robert Platt

Offline reinforcement learning (RL) refers to the problem of learning policies from a static dataset of environment interactions. Offline RL enables extensive use and re-use of historical datasets, while also alleviating safety concerns…

Machine Learning · Computer Science 2020-12-22 Rafael Rafailov , Tianhe Yu , Aravind Rajeswaran , Chelsea Finn

Reinforcement Learning (RL) training is predominantly conducted in cost-effective and controlled simulation environments. However, the transfer of these trained models to real-world tasks often presents unavoidable challenges. This research…

Deep learning and reinforcement learning methods have recently been used to solve a variety of problems in continuous control domains. An obvious application of these techniques is dexterous manipulation tasks in robotics which are…

Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving…

Artificial Intelligence · Computer Science 2021-07-02 Lunjun Zhang , Ge Yang , Bradly C. Stadie

Dexterous grasping in the real world presents a fundamental and significant challenge for robot learning. The ability to employ affordance-aware poses to grasp objects with diverse geometries and properties in arbitrary scenarios is…

Robotics · Computer Science 2025-09-23 Dongchi Huang , Tianle Zhang , Yihang Li , Ling Zhao , Jiayi Li , Zhirui Fang , Chunhe Xia , Xiaodong He

World models, which are predictive representations of how environments evolve under actions, have become a central component of robot learning. They support policy learning, planning, simulation, evaluation, data generation, and have…

We present a general, two-stage reinforcement learning approach to create robust policies that can be deployed on real robots without any additional training using a single demonstration generated by trajectory optimization. The…

Robotics · Computer Science 2022-01-25 Miroslav Bogdanovic , Majid Khadiv , Ludovic Righetti

Offline Safe Reinforcement Learning (RL) seeks to address safety constraints by learning from static datasets and restricting exploration. However, these approaches heavily rely on the dataset and struggle to generalize to unseen scenarios…

Robotics · Computer Science 2025-03-04 Chenyang Cao , Yucheng Xin , Silang Wu , Longxiang He , Zichen Yan , Junbo Tan , Xueqian Wang

Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which…

Robotics · Computer Science 2026-03-09 Liangzhi Shi , Shuaihang Chen , Feng Gao , Yinuo Chen , Kang Chen , Tonghe Zhang , Hongzhi Zang , Weinan Zhang , Chao Yu , Yu Wang

Generalizing locomotion policies across diverse legged robots with varying morphologies is a key challenge due to differences in observation/action dimensions and system dynamics. In this work, we propose Multi-Loco, a novel unified…

Robotics · Computer Science 2025-06-16 Shunpeng Yang , Zhen Fu , Zhefeng Cao , Guo Junde , Patrick Wensing , Wei Zhang , Hua Chen

Real-life control tasks involve matters of various substances---rigid or soft bodies, liquid, gas---each with distinct physical behaviors. This poses challenges to traditional rigid-body physics engines. Particle-based simulators have been…

Machine Learning · Computer Science 2019-04-19 Yunzhu Li , Jiajun Wu , Russ Tedrake , Joshua B. Tenenbaum , Antonio Torralba

In this paper, we explore deep reinforcement learning algorithms for vision-based robotic grasping. Model-free deep reinforcement learning (RL) has been successfully applied to a range of challenging environments, but the proliferation of…

Robotics · Computer Science 2018-03-30 Deirdre Quillen , Eric Jang , Ofir Nachum , Chelsea Finn , Julian Ibarz , Sergey Levine

Real-world robotic manipulation tasks remain an elusive challenge, since they involve both fine-grained environment interaction, as well as the ability to plan for long-horizon goals. Although deep reinforcement learning (RL) methods have…

Machine Learning · Computer Science 2023-03-20 Núria Armengol Urpí , Marco Bagatella , Otmar Hilliges , Georg Martius , Stelian Coros

We tackle the problem of learning complex, general behaviors directly in the real world. We propose an approach for robots to efficiently learn manipulation skills using only a handful of real-world interaction trajectories from many…

Robotics · Computer Science 2023-08-22 Russell Mendonca , Shikhar Bahl , Deepak Pathak

Model-free reinforcement learning has recently been shown to be effective at learning navigation policies from complex image input. However, these algorithms tend to require large amounts of interaction with the environment, which can be…

Robotics · Computer Science 2018-07-17 Jake Bruce , Niko Sünderhauf , Piotr Mirowski , Raia Hadsell , Michael Milford

Data-driven simulation has become a favorable way to train and test autonomous driving algorithms. The idea of replacing the actual environment with a learned simulator has also been explored in model-based reinforcement learning in the…

Robotics · Computer Science 2023-09-29 Zhejun Zhang , Alexander Liniger , Dengxin Dai , Fisher Yu , Luc Van Gool

3D world models (i.e., learning-based 3D dynamics models) offer a promising approach to generalizable robotic manipulation by capturing the underlying physics of environment evolution conditioned on robot actions. However, existing 3D world…

Robotics · Computer Science 2025-08-27 Suning Huang , Qianzhong Chen , Xiaohan Zhang , Jiankai Sun , Mac Schwager