English
Related papers

Related papers: OAT: Ordered Action Tokenization

200 papers

Unsupervised action segmentation has recently pushed its limits with ASOT, an optimal transport (OT)-based method that simultaneously learns action representations and performs clustering using pseudo-labels. Unlike other OT-based…

Computer Vision and Pattern Recognition · Computer Science 2025-08-08 Elena Bueno-Benito , Mariella Dimiccoli

We consider statistical learning problems in which data are observed as a set of probability measures. Optimal transport (OT) is a popular tool to compare and manipulate such objects, but its computational cost becomes prohibitive when the…

Machine Learning · Statistics 2026-03-24 Erell Gachon , Elsa Cazelles , Jérémie Bigot

The subject of this paper is reinforcement learning. Policies are considered here that produce actions based on states and random elements autocorrelated in subsequent time instants. Consequently, an agent learns from experiments that are…

Machine Learning · Computer Science 2020-09-11 Marcin Szulc , Jakub Łyskawa , Paweł Wawrzyński

Alignment plays a fundamental role in many machine learning problems, such as multi-network analysis, multimodal learning, and point cloud registration. Recent works increasingly leverage optimal transport (OT) for distributional alignment,…

Machine Learning · Computer Science 2026-05-26 Qi Yu , Ruizhong Qiu , Zhichen Zeng , My T. Thai , Huan Liu , Hanghang Tong

Robot chain-of-thought reasoning (CoT) -- wherein a model predicts helpful intermediate representations before choosing actions -- provides an effective method for improving the generalization and performance of robot policies, especially…

Robotics · Computer Science 2025-05-20 William Chen , Suneel Belkhale , Suvir Mirchandani , Oier Mees , Danny Driess , Karl Pertsch , Sergey Levine

As multi-object tracking (MOT) tasks continue to evolve toward more general and multi-modal scenarios, the rigid and task-specific architectures of existing MOT methods increasingly hinder their applicability across diverse tasks and limit…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Lianjie Jia , Yuhan Wu , Binghao Ran , Yifan Wang , Lijun Wang , Huchuan Lu

When an autonomous robot learns how to execute actions, it is of interest to know if and when the execution policy can be generalised to variations of the learning scenarios. This can inform the robot about the necessity of additional…

Robotics · Computer Science 2021-07-21 Alex Mitrevski , Paul G. Plöger , Gerhard Lakemeyer

Large-scale data is an essential component of machine learning as demonstrated in recent advances in natural language processing and computer vision research. However, collecting large-scale robotic data is much more expensive and slower as…

Robotics · Computer Science 2023-06-05 Shivin Dass , Karl Pertsch , Hejia Zhang , Youngwoon Lee , Joseph J. Lim , Stefanos Nikolaidis

Current transformer-based imitation learning approaches introduce discrete action representations and train an autoregressive transformer decoder on the resulting latent code. However, the initial quantization breaks the continuous…

Machine Learning · Computer Science 2025-12-09 Ziyad Sheebaelhamd , Michael Tschannen , Michael Muehlebach , Claire Vernade

Behavioral cloning has proven to be effective for learning sequential decision-making policies from expert demonstrations. However, behavioral cloning often suffers from the causal confusion problem where a policy relies on the noticeable…

Machine Learning · Computer Science 2021-10-28 Jongjin Park , Younggyo Seo , Chang Liu , Li Zhao , Tao Qin , Jinwoo Shin , Tie-Yan Liu

Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions, measuring and mitigating scheming requires different…

Learning robot policies using imitation learning requires collecting large amounts of costly action-labeled expert demonstrations, which fundamentally limits the scale of training data. A promising approach to address this bottleneck is to…

Robotics · Computer Science 2025-05-12 Anthony Liang , Pavel Czempin , Matthew Hong , Yutai Zhou , Erdem Biyik , Stephen Tu

Learning visuomotor policy for multi-task robotic manipulation has been a long-standing challenge for the robotics community. The difficulty lies in the diversity of action space: typically, a goal can be accomplished in multiple ways,…

Robotics · Computer Science 2025-03-24 Kun Wu , Yichen Zhu , Jinming Li , Junjie Wen , Ning Liu , Zhiyuan Xu , Jian Tang

Fine-tuning large language models (LLMs) using zeroth-order optimization (ZO) offers a memory-efficient alternative to gradient-based methods but suffers from slower convergence and unstable optimization due to noisy gradient estimates.…

Machine Learning · Computer Science 2025-06-24 Jikai Long , Zijian Hu , Xiaodong Yu , Jianwen Xie , Zhaozhuo Xu

Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often use inverse reinforcement learning (IRL), where given a set of expert…

Robotics · Computer Science 2023-02-22 Siddhant Haldar , Vaibhav Mathur , Denis Yarats , Lerrel Pinto

We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action spaces. Our algorithm is based on optimistic one-step value…

Machine Learning · Computer Science 2020-10-26 Sean R. Sinclair , Tianyu Wang , Gauri Jain , Siddhartha Banerjee , Christina Lee Yu

The ability to learn robust policies while generalizing over large discrete action spaces is an open challenge for intelligent systems, especially in noisy environments that face the curse of dimensionality. In this paper, we present a…

Machine Learning · Computer Science 2023-06-29 Pranavi Pathakota , Hardik Meisheri , Harshad Khadilkar

Autoregressive image generation aims to predict the next token based on previous ones. However, this process is challenged by the bidirectional dependencies inherent in conventional image tokenizations, which creates a fundamental…

Computer Vision and Pattern Recognition · Computer Science 2026-02-17 Pingyu Wu , Kai Zhu , Yu Liu , Longxiang Tang , Jian Yang , Yansong Peng , Wei Zhai , Yang Cao , Zheng-Jun Zha

Reinforcement learning (RL) has become a key driver of progress in large language models, but scaling RL to long chain-of-thought (CoT) trajectories is increasingly constrained by backpropagation over every generated token. Even with…

Machine Learning · Computer Science 2026-03-10 Hejian Sang , Yuanda Xu , Zhengze Zhou , Ran He , Zhipeng Wang

While deep reinforcement learning techniques have recently produced considerable achievements on many decision-making problems, their use in robotics has largely been limited to simulated worlds or restricted motions, since unconstrained…

Robotics · Computer Science 2018-02-26 Tu-Hoa Pham , Giovanni De Magistris , Ryuki Tachibana