English
Related papers

Related papers: MOTO: Offline Pre-training to Online Fine-tuning f…

200 papers

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

A long-standing goal in AI is to develop agents capable of solving diverse tasks across a range of environments, including those never seen during training. Two dominant paradigms address this challenge: (i) reinforcement learning (RL),…

Machine Learning · Computer Science 2025-10-30 Vlad Sobal , Wancong Zhang , Kyunghyun Cho , Randall Balestriero , Tim G. J. Rudner , Yann LeCun

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

Accurate dynamics models are critical for the design of predictive controller for autonomous mobile robots. Physics-based models are often too simple to capture relevant real-world effects, while data-driven models are data-intensive and…

Robotics · Computer Science 2026-04-07 Abdullah Altawaitan , Nikolay Atanasov

Reinforcement Learning (RL) has been successful in various domains like robotics, game playing, and simulation. While RL agents have shown impressive capabilities in their specific tasks, they insufficiently adapt to new tasks. In…

Machine Learning · Computer Science 2023-10-30 Thomas Schmied , Markus Hofmarcher , Fabian Paischer , Razvan Pascanu , Sepp Hochreiter

Model-based approaches for planning and control for bipedal locomotion have a long history of success. It can provide stability and safety guarantees while being effective in accomplishing many locomotion tasks. Model-free reinforcement…

Robotics · Computer Science 2023-10-17 Yu-Ming Chen , Hien Bui , Michael Posa

Offline reinforcement learning (RL) provides a promising approach to avoid costly online interaction with the real environment. However, the performance of offline RL highly depends on the quality of the datasets, which may cause…

Robotics · Computer Science 2024-05-08 Yiwen Hou , Haoyuan Sun , Jinming Ma , Feng Wu

To obtain a near-optimal policy with fewer interactions in Reinforcement Learning (RL), a promising approach involves the combination of offline RL, which enhances sample efficiency by leveraging offline datasets, and online RL, which…

Machine Learning · Computer Science 2024-11-18 Xiaoyu Wen , Xudong Yu , Rui Yang , Haoyuan Chen , Chenjia Bai , Zhen Wang

Offline reinforcement learning (ORL) holds great promise for robot learning due to its ability to learn from arbitrary pre-generated experience. However, current ORL benchmarks are almost entirely in simulation and utilize contrived…

Robotics · Computer Science 2022-10-14 Gaoyue Zhou , Liyiming Ke , Siddhartha Srinivasa , Abhinav Gupta , Aravind Rajeswaran , Vikash Kumar

Fine-tuning has proven to be highly effective in adapting pre-trained models to perform better on new desired tasks with minimal data samples. Among the most widely used approaches are reparameterization methods, which update a target…

Machine Learning · Computer Science 2025-10-27 Aymane El Firdoussi , El Mahdi Chayti , Mohamed El Amine Seddik , Martin Jaggi

Offline reinforcement learning (RL) seeks to learn optimal policies from static datasets without interacting with the environment. A common challenge is handling multi-modal action distributions, where multiple behaviours are represented in…

Machine Learning · Computer Science 2025-03-20 Mianchu Wang , Yue Jin , Giovanni Montana

Reinforcement learning (RL) has shown great promise with algorithms learning in environments with large state and action spaces purely from scalar reward signals. A crucial challenge for current deep RL algorithms is that they require a…

Machine Learning · Computer Science 2023-11-23 Shivakanth Sujit , Pedro H. M. Braga , Jorg Bornschein , Samira Ebrahimi Kahou

Humans and animals can learn complex predictive models that allow them to accurately and reliably reason about real-world phenomena, and they can adapt such models extremely quickly in the face of unexpected changes. Deep neural network…

Machine Learning · Computer Science 2019-01-30 Anusha Nagabandi , Chelsea Finn , Sergey Levine

Reinforcement learning (RL) provides an appealing formalism for learning control policies from experience. However, the classic active formulation of RL necessitates a lengthy active exploration process for each behavior, making it…

Machine Learning · Computer Science 2021-04-27 Ashvin Nair , Abhishek Gupta , Murtaza Dalal , Sergey Levine

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

Humans are experts at high-fidelity imitation -- closely mimicking a demonstration, often in one attempt. Humans use this ability to quickly solve a task instance, and to bootstrap learning of new tasks. Achieving these abilities in…

Equipping quadruped robots with manipulators provides unique loco-manipulation capabilities, enabling diverse practical applications. This integration creates a more complex system that has increased difficulties in modeling and control.…

Robotics · Computer Science 2025-07-08 Dianyong Hou , Chengrui Zhu , Zhen Zhang , Zhibin Li , Chuang Guo , Yong Liu

Model-based approaches are becoming increasingly popular in the field of offline reinforcement learning, with high potential in real-world applications due to the model's capability of thoroughly utilizing the large historical datasets…

Machine Learning · Computer Science 2023-05-08 Haoyang He

Model-based offline reinforcement learning (RL), which builds a supervised transition model with logging dataset to avoid costly interactions with the online environment, has been a promising approach for offline policy optimization. As the…

Machine Learning · Computer Science 2023-09-06 Junming Yang , Xingguo Chen , Shengyuan Wang , Bolei Zhang

Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on low-dimensional…

Machine Learning · Computer Science 2024-03-18 Zohar Rimon , Tom Jurgenson , Orr Krupnik , Gilad Adler , Aviv Tamar