English
Related papers

Related papers: OAT: Ordered Action Tokenization

200 papers

Deep reinforcement learning agents frequently suffer from premature convergence, where early entropy collapse causes the policy to discard exploratory behaviors before discovering globally optimal strategies. We introduce Optimistic Policy…

Machine Learning · Computer Science 2026-03-10 Mai Pham , Vikrant Vaze , Peter Chin

Training manipulation policies for humanoid robots with diverse data enhances their robustness and generalization across tasks and platforms. However, learning solely from robot demonstrations is labor-intensive, requiring expensive…

Allocation tasks represent a class of problems where a limited amount of resources must be allocated to a set of entities at each time step. Prominent examples of this task include portfolio optimization or distributing computational…

Artificial Intelligence · Computer Science 2024-09-30 David Winkel , Niklas Strauß , Maximilian Bernhard , Zongyue Li , Thomas Seidl , Matthias Schubert

Unsupervised object-centric learning aims to decompose scenes into interpretable object entities, termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them, crucial aspects include guiding the encoder…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Ioannis Kakogeorgiou , Spyros Gidaris , Konstantinos Karantzalos , Nikos Komodakis

Optimal transport (OT) is a popular tool in machine learning to compare probability measures geometrically, but it comes with substantial computational burden. Linear programming algorithms for computing OT distances scale cubically in the…

Machine Learning · Computer Science 2022-03-24 Gaspard Beugnot , Aude Genevay , Kristjan Greenewald , Justin Solomon

Understanding a person's behavior from their 3D motion is a fundamental problem in computer vision with many applications. An important component of this problem is 3D Temporal Action Localization (3D-TAL), which involves recognizing what…

Computer Vision and Pattern Recognition · Computer Science 2022-03-22 Jiankai Sun , Bolei Zhou , Michael J. Black , Arjun Chandrasekaran

Reinforcement learning often requires extensive training data. Simulation-to-real transfer offers a promising approach to address this challenge in robotics. While differentiable simulators offer improved sample efficiency through exact…

Robotics · Computer Science 2024-12-02 Severin Bochem , Eduardo Gonzalez-Sanchez , Yves Bicker , Gabriele Fadini

A robot's instantaneous sensory observations do not always reveal task-relevant state information. Under such partial observability, optimal behavior typically involves explicitly acting to gain the missing information. Today's standard…

Human motion prediction, which aims at predicting future human skeletons given the past ones, is a typical sequence-to-sequence problem. Therefore, extensive efforts have been continued on exploring different RNN-based encoder-decoder…

Computer Vision and Pattern Recognition · Computer Science 2021-02-24 Bin Li , Jian Tian , Zhongfei Zhang , Hailin Feng , Xi Li

Vision-Language-Action (VLA) models rely on current observations, including images, language instructions, and robot states, to predict actions and complete tasks. While accurate visual perception is crucial for precise action prediction…

Computer Vision and Pattern Recognition · Computer Science 2026-03-03 Cheng Yang , Jianhao Jiao , Lingyi Huang , Jinqi Xiao , Zhexiang Tang , Yu Gong , Yibiao Ying , Yang Sui , Jintian Lin , Wen Huang , Bo Yuan

Quantization-aware training (QAT) is a representative model compression method to reduce redundancy in weights and activations. However, most existing QAT methods require end-to-end training on the entire dataset, which suffers from long…

Machine Learning · Computer Science 2024-08-21 Xijie Huang , Zechun Liu , Shih-Yang Liu , Kwang-Ting Cheng

By thoroughly revisiting the classic human action recognition paradigm, this paper aims at proposing a new approach for the design of effective action classification systems. Taking as testbed publicly available three-dimensional (MoCap)…

Computer Vision and Pattern Recognition · Computer Science 2016-05-03 Andrea Zunino , Jacopo Cavazza , Vittorio Murino

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

Computation and Language · Computer Science 2024-06-25 Allmin Balloccu , Jack Zhang

The ability to learn from large batches of autonomously collected data for policy improvement -- a paradigm we refer to as batch online reinforcement learning -- holds the promise of enabling truly scalable robot learning by significantly…

Robotics · Computer Science 2025-05-14 Perry Dong , Suvir Mirchandani , Dorsa Sadigh , Chelsea Finn

We introduce GROOT, an imitation learning method for learning robust policies with object-centric and 3D priors. GROOT builds policies that generalize beyond their initial training conditions for vision-based manipulation. It constructs…

Robotics · Computer Science 2023-10-24 Yifeng Zhu , Zhenyu Jiang , Peter Stone , Yuke Zhu

Option discovery and skill acquisition frameworks are integral to the functioning of a Hierarchically organized Reinforcement learning agent. However, such techniques often yield a large number of options or skills, which can potentially be…

Machine Learning · Computer Science 2020-07-06 Arjun Manoharan , Rahul Ramesh , Balaraman Ravindran

Current quantization-aware training (QAT) methods primarily focus on enhancing the performance of quantized models on in-distribution (I.D) data, while overlooking the potential performance degradation on out-of-distribution (OOD) data. In…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Jiacheng Jiang , Yuan Meng , Chen Tang , Han Yu , Qun Li , Zhi Wang , Wenwu Zhu

The Transformer, a highly expressive architecture for sequence modeling, has recently been adapted to solve sequential decision-making, most notably through the Decision Transformer (DT), which learns policies by conditioning on desired…

Machine Learning · Computer Science 2025-10-15 Xiaohang Tang , Zhuowen Cheng , Satyabrat Kumar

Assistive robots enable people with disabilities to conduct everyday tasks on their own. However, these tasks can be complex, containing both coarse reaching motions and fine-grained manipulation. For example, when eating, not only does one…

Robotics · Computer Science 2020-05-12 Hong Jun Jeon , Dylan P. Losey , Dorsa Sadigh

Outside of transfer learning settings, reinforcement learning agents start their learning process from a clean slate. As a result, such agents have to go through a slow process to learn even the most obvious skills required to solve a…

Machine Learning · Computer Science 2025-05-20 Rubens O. Moraes , Quazi Asif Sadmine , Hendrik Baier , Levi H. S. Lelis