English
Related papers

Related papers: Imitation Learning Policy based on Multi-Step Cons…

200 papers

Recent years have witnessed impressive robotic manipulation systems driven by advances in imitation learning and generative modeling, such as diffusion- and flow-based approaches. As robot policy performance increases, so does the…

A promising way to improve the sample efficiency of reinforcement learning is model-based methods, in which many explorations and evaluations can happen in the learned models to save real-world samples. However, when the learned model has a…

Machine Learning · Computer Science 2022-09-14 Haoxin Lin , Yihao Sun , Jiaji Zhang , Yang Yu

Autonomous racing with scaled race cars has gained increasing attention as an effective approach for developing perception, planning and control algorithms for safe autonomous driving at the limits of the vehicle's handling. To train agile…

Robotics · Computer Science 2023-05-30 Xiatao Sun , Mingyan Zhou , Zhijun Zhuang , Shuo Yang , Johannes Betz , Rahul Mangharam

Generative models based on dynamical equations such as flows and diffusions offer exceptional sample quality, but require computationally expensive numerical integration during inference. The advent of consistency models has enabled…

Machine Learning · Computer Science 2025-06-04 Nicholas M. Boffi , Michael S. Albergo , Eric Vanden-Eijnden

In this paper, we unify more than 10 existing one-step diffusion distillation approaches, such as Diff-Instruct, DMD, SIM, SiD, $f$-distill, etc, inside a theory-driven framework which we name the \textbf{\emph{Uni-Instruct}}. Uni-Instruct…

Machine Learning · Computer Science 2025-10-23 Yifei Wang , Weimin Bai , Colin Zhang , Debing Zhang , Weijian Luo , He Sun

In this paper, we leverage the rapid advances in imitation learning, a topic of intense recent focus in the Reinforcement Learning (RL) literature, to develop new sample complexity results and performance guarantees for data-driven Model…

Optimization and Control · Mathematics 2022-10-18 Kwangjun Ahn , Zakaria Mhammedi , Horia Mania , Zhang-Wei Hong , Ali Jadbabaie

Generative manipulation policies can fail catastrophically under deployment-time distribution shift, yet many failures are near-misses: the robot reaches almost-correct poses and would succeed with a small corrective motion. We propose…

Robotics · Computer Science 2026-03-05 Edgar Welte , Yitian Shi , Rosa Wolf , Maximillian Gilles , Rania Rayyes

Machine learning models often incorporate vast amounts of data, raising significant privacy concerns. Machine unlearning, the ability to remove the influence of specific data points from a trained model, addresses these concerns. This paper…

Machine Learning · Computer Science 2024-06-14 David Zagardo

This paper introduces DLM-One, a score-distillation-based framework for one-step sequence generation with continuous diffusion language models (DLMs). DLM-One eliminates the need for iterative refinement by aligning the scores of a student…

Computation and Language · Computer Science 2025-06-03 Tianqi Chen , Shujian Zhang , Mingyuan Zhou

The unsupervised task of aligning two or more distributions in a shared latent space has many applications including fair representations, batch effect mitigation, and unsupervised domain adaptation. Existing flow-based approaches estimate…

Machine Learning · Computer Science 2022-03-17 Zeyu Zhou , Ziyu Gong , Pradeep Ravikumar , David I. Inouye

We propose a hybrid approach aimed at improving the sample efficiency in goal-directed reinforcement learning. We do this via a two-step mechanism where firstly, we approximate a model from Model-Free reinforcement learning. Then, we…

Machine Learning · Computer Science 2019-01-09 Shoubhik Debnath , Gaurav Sukhatme , Lantao Liu

Diffusion distillation is a widely used technique to reduce the sampling cost of diffusion models, yet it often requires extensive training, and the student performance tends to be degraded. Recent studies show that incorporating a GAN…

Machine Learning · Computer Science 2025-06-12 Bowen Zheng , Tianming Yang

Many existing imitation learning datasets are collected from multiple demonstrators, each with different expertise at different parts of the environment. Yet, standard imitation learning algorithms typically treat all demonstrators as…

Machine Learning · Computer Science 2022-06-14 Mark Beliaev , Andy Shih , Stefano Ermon , Dorsa Sadigh , Ramtin Pedarsani

Recently, diffusion models have achieved significant advances in vision, text, and robotics. However, they still face slow generation speeds due to sequential denoising processes. To address this, a parallel sampling method based on Picard…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Junhyuk So , Jiwoong Shin , Chaeyeon Jang , Eunhyeok Park

High-frequency trading (HFT) is an investing strategy that continuously monitors market states and places bid and ask orders at millisecond speeds. Traditional HFT approaches fit models with historical data and assume that future market…

Trading and Market Microstructure · Quantitative Finance 2025-05-23 Yang Li , Zhi Chen , Steve Yang

Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control. For example, this issue often limits the performance of model-based reinforcement learning and imitation…

Systems and Control · Electrical Eng. & Systems 2025-04-03 Anne Somalwar , Bruce D. Lee , George J. Pappas , Nikolai Matni

The performance of optimization-based robot motion planning algorithms is highly dependent on the initial solutions, commonly obtained by running a sampling-based planner to obtain a collision-free path. However, these methods can be slow…

Robotics · Computer Science 2025-08-15 J. Carvalho , A. Le , P. Kicki , D. Koert , J. Peters

Robotic skills can be learned via imitation learning (IL) using user-provided demonstrations, or via reinforcement learning (RL) using large amountsof autonomously collected experience.Both methods have complementarystrengths and…

Imposing consistency through proxy tasks has been shown to enhance data-driven learning and enable self-supervision in various tasks. This paper introduces novel and effective consistency strategies for optical flow estimation, a problem…

Computer Vision and Pattern Recognition · Computer Science 2022-05-25 Jisoo Jeong , Jamie Menjay Lin , Fatih Porikli , Nojun Kwak

Recent years have witnessed many successful trials in the robot learning field. For contact-rich robotic tasks, it is challenging to learn coordinated motor skills by reinforcement learning. Imitation learning solves this problem by using a…

Robotics · Computer Science 2023-11-02 Linqi Ye , Jiayi Li , Yi Cheng , Xianhao Wang , Bin Liang , Yan Peng