English
Related papers

Related papers: Not Only Domain Randomization: Universal Policy wi…

200 papers

While reinforcement learning has achieved considerable successes in recent years, state-of-the-art models are often still limited by the size of state and action spaces. Model-free reinforcement learning approaches use some form of state…

Machine Learning · Computer Science 2021-08-23 Paul J. Pritz , Liang Ma , Kin K. Leung

Sample complexity and safety are major challenges when learning policies with reinforcement learning for real-world tasks, especially when the policies are represented using rich function approximators like deep neural networks. Model-based…

Machine Learning · Computer Science 2017-03-07 Aravind Rajeswaran , Sarvjeet Ghotra , Balaraman Ravindran , Sergey Levine

Domain adaptation (DA) is the task of classifying an unlabeled dataset (target) using a labeled dataset (source) from a related domain. The majority of successful DA methods try to directly match the distributions of the source and target…

Machine Learning · Statistics 2018-03-22 Twan van Laarhoven , Elena Marchiori

Unsupervised domain adaptation is effective in leveraging the rich information from the source domain to the unsupervised target domain. Though deep learning and adversarial strategy make an important breakthrough in the adaptability of…

Machine Learning · Computer Science 2020-03-02 You-Wei Luo , Chuan-Xian Ren , Pengfei Ge , Ke-Kun Huang , Yu-Feng Yu

Embodied perception systems face severe challenges of dynamic environment distribution drift when they continuously interact in open physical spaces. However, the existing domain incremental awareness methods often rely on the domain id…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Juncen Guo , Xiaoguang Zhu , Jingyi Wu , Jingyu Zhang , Jingnan Cai , Zhenghao Niu , Liang Song

Humanoids have the potential to be the ideal embodiment in environments designed for humans. Thanks to the structural similarity to the human body, they benefit from rich sources of demonstration data, e.g., collected via teleoperation,…

Robotics · Computer Science 2024-11-05 Oleg Kaidanov , Firas Al-Hafez , Yusuf Suvari , Boris Belousov , Jan Peters

Modern reinforcement learning methods suffer from low sample efficiency and unsafe exploration, making it infeasible to train robotic policies entirely on real hardware. In this work, we propose to address the problem of sim-to-real domain…

Computer Vision and Pattern Recognition · Computer Science 2019-10-01 Karol Arndt , Murtaza Hazara , Ali Ghadirzadeh , Ville Kyrki

Safe policy improvement (SPI) is an offline reinforcement learning problem in which a new policy that reliably outperforms the behavior policy with high confidence needs to be computed using only a dataset and the behavior policy. Markov…

Artificial Intelligence · Computer Science 2025-08-20 Kasper Engelen , Guillermo A. Pérez , Marnix Suilen

We develop an optimization framework centered around a core idea: once a (parametric) policy is specified, control authority is transferred to the policy, resulting in an autonomous dynamical system. Thus we should be able to optimize…

Machine Learning · Computer Science 2025-06-11 Emo Todorov

We study the problem of identifying the policy space of a learning agent, having access to a set of demonstrations generated by its optimal policy. We introduce an approach based on statistical testing to identify the set of policy…

Machine Learning · Computer Science 2019-09-10 Alberto Maria Metelli , Guglielmo Manneschi , Marcello Restelli

Sim-to-real transfer remains a significant challenge in robotics due to the discrepancies between simulated and real-world dynamics. Traditional methods like Domain Randomization often fail to capture fine-grained dynamics, limiting their…

Robotics · Computer Science 2025-03-04 Xilun Zhang , Shiqi Liu , Peide Huang , William Jongwon Han , Yiqi Lyu , Mengdi Xu , Ding Zhao

Reinforcement learning (RL) has demonstrated great success in the past several years. However, most of the scenarios focus on simulated environments. One of the main challenges of transferring the policy learned in a simulated environment…

Robotics · Computer Science 2021-02-24 Ya-Yen Tsai , Hui Xu , Zihan Ding , Chong Zhang , Edward Johns , Bidan Huang

In modern robotics, effectively computing optimal control policies under dynamically varying environments poses substantial challenges to the off-the-shelf parametric policy gradient methods, such as the Deep Deterministic Policy Gradient…

Robotics · Computer Science 2022-03-29 Apan Dastider , Mingjie Lin

Domain randomization in reinforcement learning is an established technique for increasing the robustness of control policies trained in simulation. By randomizing environment properties during training, the learned policy can become robust…

Bayesian approaches developed to solve the optimal design of sequential experiments are mathematically elegant but computationally challenging. Recently, techniques using amortization have been proposed to make these Bayesian approaches…

Machine Learning · Computer Science 2022-06-20 Tom Blau , Edwin V. Bonilla , Iadine Chades , Amir Dezfouli

In many real-world decision making problems, reaching an optimal decision requires taking into account a variable number of objects around the agent. Autonomous driving is a domain in which this is especially relevant, since the number of…

Machine Learning · Computer Science 2020-08-13 Maria Hügle , Gabriel Kalweit , Branka Mirchevska , Moritz Werling , Joschka Boedecker

Model-based reinforcement learning approaches carry the promise of being data efficient. However, due to challenges in learning dynamics models that sufficiently match the real-world dynamics, they struggle to achieve the same asymptotic…

Machine Learning · Computer Science 2018-09-17 Ignasi Clavera , Jonas Rothfuss , John Schulman , Yasuhiro Fujita , Tamim Asfour , Pieter Abbeel

We introduce UMI-on-Air, a framework for embodiment-aware deployment of embodiment-agnostic manipulation policies. Our approach leverages diverse, unconstrained human demonstrations collected with a handheld gripper (UMI) to train…

Robotics · Computer Science 2026-03-17 Harsh Gupta , Xiaofeng Guo , Huy Ha , Chuer Pan , Muqing Cao , Dongjae Lee , Sebastian Scherer , Shuran Song , Guanya Shi

We present a new approach for transfer of dynamic robot control policies such as biped locomotion from simulation to real hardware. Key to our approach is to perform system identification of the model parameters {\mu} of the hardware (e.g.…

Robotics · Computer Science 2019-08-27 Wenhao Yu , Visak CV Kumar , Greg Turk , C. Karen Liu

In offline reinforcement learning, deriving an effective policy from a pre-collected set of experiences is challenging due to the distribution mismatch between the target policy and the behavioral policy used to collect the data, as well as…

Machine Learning · Computer Science 2024-12-10 Catalin E. Brita , Stephan Bongers , Frans A. Oliehoek