English
Related papers

Related papers: Policy Transfer via Kinematic Domain Randomization…

200 papers

Training robots with reinforcement learning (RL) typically involves heavy interactions with the environment, and the acquired skills are often sensitive to changes in task environments and robot kinematics. Transfer RL aims to leverage…

Robotics · Computer Science 2023-09-26 Pingcheng Jian , Easop Lee , Zachary Bell , Michael M. Zavlanos , Boyuan Chen

Humans decompose novel complex tasks into simpler ones to exploit previously learned skills. Analogously, hierarchical reinforcement learning seeks to leverage lower-level policies for simple tasks to solve complex ones. However, because…

Machine Learning · Computer Science 2022-03-15 Ju-Seung Byun , Andrew Perrault

Classical Domain Adaptation methods acquire transferability by regularizing the overall distributional discrepancies between features in the source domain (labeled) and features in the target domain (unlabeled). They often do not…

Machine Learning · Computer Science 2023-06-01 Shumin Ma , Zhiri Yuan , Qi Wu , Yiyan Huang , Xixu Hu , Cheuk Hang Leung , Dongdong Wang , Zhixiang Huang

We present a new algorithm for domain adaptation improving upon a discrepancy minimization algorithm previously shown to outperform a number of algorithms for this task. Unlike many previous algorithms for domain adaptation, our algorithm…

Machine Learning · Computer Science 2015-02-24 Corinna Cortes , Mehryar Mohri , Andres Muñoz Medina

Domain adaptation enables the learner to safely generalize into novel environments by mitigating domain shifts across distributions. Previous works may not effectively uncover the underlying reasons that would lead to the drastic model…

Computer Vision and Pattern Recognition · Computer Science 2019-08-05 Ruijia Xu , Guanbin Li , Jihan Yang , Liang Lin

Creating accurate spatial representations that take into account uncertainty is critical for autonomous robots to safely navigate in unstructured environments. Although recent LIDAR based mapping techniques can produce robust occupancy…

Computer Vision and Pattern Recognition · Computer Science 2020-07-02 Anthony Tompkins , Ransalu Senanayake , Fabio Ramos

Learning domain adaptive policies that can generalize to unseen transition dynamics, remains a fundamental challenge in learning-based control. Substantial progress has been made through domain representation learning to capture…

Machine Learning · Computer Science 2026-03-31 Pengcheng Wang , Qinghang Liu , Haotian Lin , Yiheng Li , Guojian Zhan , Masayoshi Tomizuka , Yixiao Wang

Unsupervised reinforcement learning aims to acquire skills without prior goal representations, where an agent automatically explores an open-ended environment to represent goals and learn the goal-conditioned policy. However, this procedure…

Machine Learning · Computer Science 2021-10-27 Jinxin Liu , Hao Shen , Donglin Wang , Yachen Kang , Qiangxing Tian

Simulation has recently become key for deep reinforcement learning to safely and efficiently acquire general and complex control policies from visual and proprioceptive inputs. Tactile information is not usually considered despite its…

Robotics · Computer Science 2021-11-02 Alex Church , John Lloyd , Raia Hadsell , Nathan F. Lepora

Deep learning has revolutionized neuroimage analysis by delivering unprecedented speed and accuracy. However, the narrow scope of many training datasets constrains model robustness and generalizability. This challenge is particularly acute…

Image and Video Processing · Electrical Eng. & Systems 2025-12-08 Malte Hoffmann

This paper investigates how the performance of visual navigation policies trained in simulation compares to policies trained with real-world data. Performance degradation of simulator-trained policies is often significant when they are…

The use of deep reinforcement learning allows for high-dimensional state descriptors, but little is known about how the choice of action representation impacts the learning difficulty and the resulting performance. We compare the impact of…

Machine Learning · Computer Science 2017-10-20 Xue Bin Peng , Michiel van de Panne

We propose a simple, practical, and intuitive approach for domain adaptation in reinforcement learning. Our approach stems from the idea that the agent's experience in the source domain should look similar to its experience in the target…

Machine Learning · Computer Science 2021-04-16 Benjamin Eysenbach , Swapnil Asawa , Shreyas Chaudhari , Sergey Levine , Ruslan Salakhutdinov

The large demand for simulated data has made the reality gap a problem on the forefront of robotics. We propose a method to traverse the gap by tuning available simulation parameters. Through the optimisation of physics engine parameters,…

Robotics · Computer Science 2020-03-04 Jack Collins , Ross Brown , Jurgen Leitner , David Howard

We tackle the problem of generalization to unseen configurations for dynamic tasks in the real world while learning from high-dimensional image input. The family of nonlinear dynamical system-based methods have successfully demonstrated…

Machine Learning · Computer Science 2021-07-13 Shikhar Bahl , Abhinav Gupta , Deepak Pathak

Achieving quadruped robot locomotion across diverse and dynamic terrains presents significant challenges, primarily due to the discrepancies between simulation environments and real-world conditions. Traditional sim-to-real transfer methods…

Robotics · Computer Science 2026-04-06 Junyang Liang , Yuxuan Liu , Yabin Chang , Junfan Lin , Junkai Ji , Hui Li , Changxin Huang , Jianqiang Li

Acquiring dynamics is an essential topic in robot learning, but up-to-date methods, such as dynamics randomization, need to restart to check nominal parameters, generate simulation data, and train networks whenever they face different…

Robotics · Computer Science 2021-04-07 Dengpeng Xing , Jiale Li , Yiming Yang , Bo Xu

Whole-body control of robotic manipulators with awareness of full-arm kinematics is crucial for many manipulation scenarios involving body collision avoidance or body-object interactions, which makes it insufficient to consider only the…

Robotics · Computer Science 2025-12-22 Kangchen Lv , Mingrui Yu , Yongyi Jia , Chenyu Zhang , Xiang Li

Reinforcement learning (RL) problems over general state and action spaces are notoriously challenging. In contrast to the tableau setting, one can not enumerate all the states and then iteratively update the policies for each state. This…

Machine Learning · Computer Science 2026-03-24 Caleb Ju , Guanghui Lan

Reinforcement learning has shown a wide usage in robotics tasks, such as insertion and grasping. However, without a practical sim2real strategy, the policy trained in simulation could fail on the real task. There are also wide researches in…

Robotics · Computer Science 2022-06-07 Yiwen Chen , Xue Li , Sheng Guo , Xian Yao Ng , Marcelo Ang