English
Related papers

Related papers: Offline Imitation from Observation via Primal Wass…

200 papers

This paper studies offline Imitation Learning (IL) where an agent learns to imitate an expert demonstrator without additional online environment interactions. Instead, the learner is presented with a static offline dataset of…

Machine Learning · Computer Science 2022-02-01 Jonathan D. Chang , Masatoshi Uehara , Dhruv Sreenivas , Rahul Kidambi , Wen Sun

We introduce Wasserstein Policy Optimization (WPO), an actor-critic algorithm for reinforcement learning in continuous action spaces. WPO can be derived as an approximation to Wasserstein gradient flow over the space of all policies…

Machine Learning · Computer Science 2025-05-02 David Pfau , Ian Davies , Diana Borsa , Joao G. M. Araujo , Brendan Tracey , Hado van Hasselt

The aim in imitation learning is to learn effective policies by utilizing near-optimal expert demonstrations. However, high-quality demonstrations from human experts can be expensive to obtain in large numbers. On the other hand, it is…

Machine Learning · Computer Science 2021-10-29 Mengjiao Yang , Sergey Levine , Ofir Nachum

Learning from visual observation (LfVO), aiming at recovering policies from only visual observation data, is promising yet a challenging problem. Existing LfVO approaches either only adopt inefficient online learning schemes or require…

Machine Learning · Computer Science 2023-06-23 Bohan Zhou , Ke Li , Jiechuan Jiang , Zongqing Lu

Imitation Learning from Observation (IfO) offers a powerful way to learn behaviors at large-scale: Unlike behavior cloning or offline reinforcement learning, IfO can leverage action-free demonstrations and thus circumvents the need for…

Unsupervised reinforcement learning aims to train agents to learn a handful of policies or skills in environments without external reward. These pre-trained policies can accelerate learning when endowed with external reward, and can also be…

Machine Learning · Computer Science 2021-10-18 Shuncheng He , Yuhang Jiang , Hongchang Zhang , Jianzhun Shao , Xiangyang Ji

Gaze estimation methods have significantly matured in recent years, but the large number of eye images required to train deep learning models poses significant privacy risks. In addition, the heterogeneous data distribution across different…

Human-Computer Interaction · Computer Science 2022-11-15 Mayar Elfares , Zhiming Hu , Pascal Reisert , Andreas Bulling , Ralf Küsters

The Wasserstein distance, rooted in optimal transport (OT) theory, is a popular discrepancy measure between probability distributions with various applications to statistics and machine learning. Despite their rich structure and…

Machine Learning · Statistics 2023-03-02 Sloan Nietert , Rachel Cummings , Ziv Goldfeld

Wasserstein distances are widely used in modern data analysis but pose significant computational and statistical challenges in high dimensions. The sliced Wasserstein distance alleviates these challenges by leveraging one-dimensional…

Statistics Theory · Mathematics 2026-05-21 David Rodríguez-Vítores , Eustasio del Barrio , Jean-Michel Loubes

In the field of modern high-energy physics research, there is a growing emphasis on utilizing deep learning techniques to optimize event simulation, thereby expanding the statistical sample size for more accurate physical analysis.…

Computational Physics · Physics 2025-06-16 Chu-Cheng Pan , Xiang Dong , Yu-Chang Sun , Ao-Yan Cheng , Ao-Bo Wang , Yu-Xuan Hu , Hao Cai

The score function estimator is widely used for estimating gradients of stochastic objectives in stochastic computation graphs (SCG), eg, in reinforcement learning and meta-learning. While deriving the first-order gradient estimators by…

Machine Learning · Computer Science 2018-11-07 Jakob Foerster , Gregory Farquhar , Maruan Al-Shedivat , Tim Rocktäschel , Eric P. Xing , Shimon Whiteson

We present a new scientific machine learning method that learns from data a computationally inexpensive surrogate model for predicting the evolution of a system governed by a time-dependent nonlinear partial differential equation (PDE), an…

Numerical Analysis · Mathematics 2022-02-28 Elizabeth Qian , Ionut-Gabriel Farcas , Karen Willcox

Transferring human motion skills to humanoid robots remains a significant challenge. In this study, we introduce a Wasserstein adversarial imitation learning system, allowing humanoid robots to replicate natural whole-body locomotion…

We demonstrate model-based, visual robot manipulation of linear deformable objects. Our approach is based on a state-space representation of the physical system that the robot aims to control. This choice has multiple advantages, including…

Robotics · Computer Science 2020-10-07 Mengyuan Yan , Yilin Zhu , Ning Jin , Jeannette Bohg

Offline Reinforcement Learning (RL) is an emerging field of RL in which policies are learned solely from demonstrations. Within offline RL, some environments involve balancing multiple objectives, but existing multi-objective offline RL…

Machine Learning · Computer Science 2026-05-22 Peter Adema , Karim Galliamov , Aleksey Evstratovskiy , Ross Geurts

Wasserstein distance-based distributionally robust optimization (DRO) has received much attention lately due to its ability to provide a robustness interpretation of various learning models. Moreover, many of the DRO problems that arise in…

Optimization and Control · Mathematics 2019-10-29 Jiajin Li , Sen Huang , Anthony Man-Cho So

While recent state-of-the-art results for adversarial imitation-learning algorithms are encouraging, recent works exploring the imitation learning from observation (ILO) setting, where trajectories \textit{only} contain expert observations,…

Machine Learning · Computer Science 2020-06-22 Dilip Arumugam , Debadeepta Dey , Alekh Agarwal , Asli Celikyilmaz , Elnaz Nouri , Bill Dolan

Computing pairwise Wasserstein distances is a fundamental bottleneck in data analysis pipelines. Motivated by the classical Kuratowski embedding theorem, we propose two neural architectures for learning to approximate the Wasserstein-2…

Machine Learning · Computer Science 2026-04-07 Andrew Qing He

While imitation learning provides a simple and effective framework for policy learning, acquiring consistent actions during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action…

Robotics · Computer Science 2024-07-24 Xiao Liu , Fabian Weigend , Yifan Zhou , Heni Ben Amor

Deep models, while being extremely flexible and accurate, are surprisingly vulnerable to "small, imperceptible" perturbations known as adversarial attacks. While the majority of existing attacks focus on measuring perturbations under the…

Machine Learning · Computer Science 2020-08-10 Kaiwen Wu , Allen Houze Wang , Yaoliang Yu