English
Related papers

Related papers: Identifying Latent Actions and Dynamics from Offli…

200 papers

Discrete latent spaces in variational autoencoders have been shown to effectively capture the data distribution for many real-world problems such as natural language understanding, human intent prediction, and visual scene representation.…

Machine Learning · Computer Science 2021-01-19 Masha Itkina , Boris Ivanovic , Ransalu Senanayake , Mykel J. Kochenderfer , Marco Pavone

Visuomotor policies trained via behavior cloning are vulnerable to covariate shift, where small deviations from expert trajectories can compound into failure. Common strategies to mitigate this issue involve expanding the training…

Robotics · Computer Science 2025-08-11 Zhanyi Sun , Shuran Song

Unlike the sparse label action detection task, where a single action occurs in each timestamp of a video, in a dense multi-label scenario, actions can overlap. To address this challenging task, it is necessary to simultaneously learn (i)…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Faegheh Sardari , Armin Mustafa , Philip J. B. Jackson , Adrian Hilton

Dynamical systems across many disciplines are modeled as interacting particles or agents, with interaction rules that depend on a very small number of variables (e.g. pairwise distances, pairwise differences of phases, etc...), functions of…

Machine Learning · Computer Science 2022-08-05 Jinchao Feng , Mauro Maggioni , Patrick Martin , Ming Zhong

Analysis of mathematical models in ecology and epidemiology often focuses on asymptotic dynamics, such as stable equilibria and periodic orbits. However, many systems exhibit long transient behaviors where certain aspects of the dynamics…

Dynamical Systems · Mathematics 2025-11-06 Anthony Pasion , Felicia Magpantay

We address the challenge of offline reinforcement learning using realistic data, specifically non-expert data collected through sub-optimal behavior policies. Under such circumstance, the learned policy must be safe enough to manage…

Machine Learning · Computer Science 2025-04-04 Ke Jiang , Wen Jiang , Yao Li , Xiaoyang Tan

Human-motion generation is a long-standing challenging task due to the requirement of accurately modeling complex and diverse dynamic patterns. Most existing methods adopt sequence models such as RNN to directly model transitions in the…

Computer Vision and Pattern Recognition · Computer Science 2019-12-24 Zhenyi Wang , Ping Yu , Yang Zhao , Ruiyi Zhang , Yufan Zhou , Junsong Yuan , Changyou Chen

We present a novel hierarchical model for human activity recognition. In contrast to approaches that successively recognize actions and activities, our approach jointly models actions and activities in a unified framework, and their labels…

Robotics · Computer Science 2015-03-09 Ninghang Hu , Gwenn Englebienne , Zhongyu Lou , Ben Kröse

This paper proposes a data-driven method for learning convergent control policies from offline data using Contraction theory. Contraction theory enables constructing a policy that makes the closed-loop system trajectories inherently…

Machine Learning · Computer Science 2022-02-04 Navid Rezazadeh , Maxwell Kolarich , Solmaz S. Kia , Negar Mehr

We consider the finite-horizon offline reinforcement learning (RL) setting, and are motivated by the challenge of learning the policy at any step h in dynamic programming (DP) algorithms. To learn this, it is sufficient to evaluate the…

Machine Learning · Computer Science 2025-01-22 Sanath Kumar Krishnamurthy , Tanmay Gangwani , Sumeet Katariya , Branislav Kveton , Shrey Modi , Anshuka Rangi

Data collection is crucial for learning robust world models in model-based reinforcement learning. The most prevalent strategies are to actively collect trajectories by interacting with the environment during online training or training on…

Machine Learning · Computer Science 2025-09-09 Jiaqi Chen , Ji Shi , Cansu Sancaktar , Jonas Frey , Georg Martius

In order to plan a safe maneuver an autonomous vehicle must accurately perceive its environment, and understand the interactions among traffic participants. In this paper, we aim to learn scene-consistent motion forecasts of complex urban…

Computer Vision and Pattern Recognition · Computer Science 2020-07-24 Sergio Casas , Cole Gulino , Simon Suo , Katie Luo , Renjie Liao , Raquel Urtasun

Parameterized movement primitives have been extensively used for imitation learning of robotic tasks. However, the high-dimensionality of the parameter space hinders the improvement of such primitives in the reinforcement learning (RL)…

Robotics · Computer Science 2022-02-14 Samuele Tosatto , Georgia Chalvatzaki , Jan Peters

High dimensional random dynamical systems are ubiquitous, including -- but not limited to -- cyber-physical systems, daily return on different stocks of S&P 1500 and velocity profile of interacting particle systems around McKeanVlasov…

Statistics Theory · Mathematics 2023-10-17 Muhammad Abdullah Naeem , Amir Khazraei , Miroslav Pajic

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

Practical Imitation Learning (IL) systems rely on large human demonstration datasets for successful policy learning. However, challenges lie in maintaining the quality of collected data and addressing the suboptimal nature of some…

Robotics · Computer Science 2025-05-07 Sachit Kuhar , Shuo Cheng , Shivang Chopra , Matthew Bronars , Danfei Xu

Deep generative models with latent variables have been used lately to learn joint representations and generative processes from multi-modal data. These two learning mechanisms can, however, conflict with each other and representations can…

Machine Learning · Computer Science 2023-01-24 Rogelio A. Mancisidor , Michael Kampffmeyer , Kjersti Aas , Robert Jenssen

Non-stationary environments are challenging for reinforcement learning algorithms. If the state transition and/or reward functions change based on latent factors, the agent is effectively tasked with optimizing a behavior that maximizes…

Machine Learning · Computer Science 2021-05-21 Lucas N. Alegre , Ana L. C. Bazzan , Bruno C. da Silva

We study the evolution of observables of dynamical systems. For linear systems, we show that observables satisfy a closed differential equation whose minimal order is determined by the dynamical system and observation operator. This yields…

Dynamical Systems · Mathematics 2026-03-24 Xinyu Liu , Dongbin Xiu

We study off-dynamics offline reinforcement learning, where the goal is to learn a policy from offline source and limited target datasets with mismatched dynamics. Existing methods either penalize the reward or discard source transitions…

Machine Learning · Computer Science 2026-03-19 Yihong Guo , Yu Yang , Pan Xu , Anqi Liu