English
Related papers

Related papers: Train Offline, Test Online: A Real Robot Learning …

200 papers

Recent technological advances have made it possible to build real-time, interactive spoken dialogue systems for a wide variety of applications. However, when users do not respect the limitations of such systems, performance typically…

Computation and Language · Computer Science 2007-05-23 Diane J. Litman , Shimei Pan

The rise of deep learning has caused a paradigm shift in robotics research, favoring methods that require large amounts of data. Unfortunately, it is prohibitively expensive to generate such data sets on a physical platform. Therefore,…

Robotics · Computer Science 2022-01-19 Fabio Muratore , Fabio Ramos , Greg Turk , Wenhao Yu , Michael Gienger , Jan Peters

ROBEL is an open-source platform of cost-effective robots designed for reinforcement learning in the real world. ROBEL introduces two robots, each aimed to accelerate reinforcement learning research in different task domains: D'Claw is a…

Robotics · Computer Science 2019-12-17 Michael Ahn , Henry Zhu , Kristian Hartikainen , Hugo Ponte , Abhishek Gupta , Sergey Levine , Vikash Kumar

Evaluating learned robot control policies to determine their physical task-level capabilities costs experimenter time and effort. The growing number of policies and tasks exacerbates this issue. It is impractical to test every policy on…

Robotics · Computer Science 2025-02-17 Abrar Anwar , Rohan Gupta , Zain Merchant , Sayan Ghosh , Willie Neiswanger , Jesse Thomason

Recent research has proposed a series of specialized optimization algorithms for deep multi-task models. It is often claimed that these multi-task optimization (MTO) methods yield solutions that are superior to the ones found by simply…

Machine Learning · Computer Science 2022-09-26 Derrick Xin , Behrooz Ghorbani , Ankush Garg , Orhan Firat , Justin Gilmer

Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task…

Most Reinforcement Learning (RL) methods are traditionally studied in an active learning setting, where agents directly interact with their environments, observe action outcomes, and learn through trial and error. However, allowing…

Artificial Intelligence · Computer Science 2023-10-16 Maryam Zare , Parham M. Kebria , Abbas Khosravi

Deep reinforcement learning (RL) has emerged as a promising approach for autonomously acquiring complex behaviors from low level sensor observations. Although a large portion of deep RL research has focused on applications in video games…

Robotics · Computer Science 2021-02-08 Julian Ibarz , Jie Tan , Chelsea Finn , Mrinal Kalakrishnan , Peter Pastor , Sergey Levine

Offline multi-agent reinforcement learning (MARL) is an emerging field with great promise for real-world applications. Unfortunately, the current state of research in offline MARL is plagued by inconsistencies in baselines and evaluation…

Machine Learning · Computer Science 2024-10-31 Claude Formanek , Callum Rhys Tilbury , Louise Beyers , Jonathan Shock , Arnu Pretorius

Robotics is undergoing a significant transformation powered by advances in high-level control techniques based on machine learning, giving rise to the field of robot learning. Recent progress in robot learning has been accelerated by the…

The paper describes an automated evaluation system for the learning of general Physics. The system whose name is Test on Line (ToL) is based on a questions bank from which an appropriate software generates individual multi-issue…

Physics Education · Physics 2009-11-07 A. Tartaglia , E. Tresso

Robots are improving their autonomy with minimal human supervision. However, auditable actions, transparent decision processes, and new human-robot interaction models are still missing requirements to achieve extended robot autonomy. To…

Robotics · Computer Science 2026-03-09 Milan Groshev , Eduardo Castelló Ferrer

Offline reinforcement learning (RL) aims to optimize the return given a fixed dataset of agent trajectories without additional interactions with the environment. While algorithm development has progressed rapidly, significant theoretical…

Machine Learning · Computer Science 2025-08-12 Fengdi Che

In this work, we contribute a large-scale study benchmarking the performance of multiple motion-based learning from demonstration approaches. Given the number and diversity of existing methods, it is critical that comprehensive empirical…

Robotics · Computer Science 2019-11-11 M. Asif Rana , Daphne Chen , S. Reza Ahmadzadeh , Jacob Williams , Vivian Chu , Sonia Chernova

Recently, Offline Reinforcement Learning (RL) has achieved remarkable progress with the emergence of various algorithms and datasets. However, these methods usually focus on algorithmic advancements, ignoring that many low-level…

Machine Learning · Computer Science 2023-06-02 Bingyi Kang , Xiao Ma , Yirui Wang , Yang Yue , Shuicheng Yan

Deep learning often requires the manual collection and annotation of a training set. On robotic platforms, can we partially automate this task by training the robot to be curious, i.e., to seek out beneficial training information in the…

Artificial Intelligence · Computer Science 2019-02-06 Ervin Teng , Bob Iannucci

Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances. The use of learning-based methods in multi-robot planning holds great…

Robotics · Computer Science 2021-07-27 Amanda Prorok , Jan Blumenkamp , Qingbiao Li , Ryan Kortvelesy , Zhe Liu , Ethan Stump

The title of this paper is perhaps an overclaim. Of course, the process of creating and optimizing a learned model inevitably involves multiple training runs which potentially feature different architectural designs, input and output…

Machine Learning · Computer Science 2025-06-06 Christos Sakaridis

Social Robot Navigation is the skill that allows robots to move efficiently in human-populated environments while ensuring safety, comfort, and trust. Unlike other areas of research, the scientific community has not yet achieved an…

Robotics · Computer Science 2025-10-28 Pranup Chhetri , Alejandro Torrejon , Sergio Eslava , Luis J. Manso

The use of target networks is a popular approach for estimating value functions in deep Reinforcement Learning (RL). While effective, the target network remains a compromise solution that preserves stability at the cost of slowly moving…

Machine Learning · Computer Science 2026-05-19 Ahmed Hendawy , Henrik Metternich , Théo Vincent , Mahdi Kallel , Jan Peters , Carlo D'Eramo