English
Related papers

Related papers: Learning Beam Search Policies via Imitation Learni…

200 papers

Training visual embeddings with labeled data supervision has been the de facto setup for representation learning in computer vision. Inspired by recent success of adopting masked image modeling (MIM) in self-supervised representation…

Computer Vision and Pattern Recognition · Computer Science 2023-12-05 Kaifeng Chen , Daniel Salz , Huiwen Chang , Kihyuk Sohn , Dilip Krishnan , Mojtaba Seyedhosseini

Imitation learning is a proven method for creating a policy in the absence of rewards, by leveraging expert demonstrations. In this work, we apply imitation learning to conversation. In doing so, we recover a policy capable of talking to a…

Computation and Language · Computer Science 2025-08-19 Noah Kasmanoff , Rahul Zalkikar

Imitation learning in robots, also called programing by demonstration, has made important advances in recent years, allowing humans to teach context dependant motor skills/tasks to robots. We propose to extend the usual contexts…

Artificial Intelligence · Computer Science 2012-03-13 Thomas Cederborg , Pierre-Yves Oudeyer

Despite the success of deep learning in video understanding tasks, processing every frame in a video is computationally expensive and often unnecessary in real-time applications. Frame selection aims to extract the most informative and…

Computer Vision and Pattern Recognition · Computer Science 2023-04-21 Mingjun Zhao , Yakun Yu , Xiaoli Wang , Lei Yang , Di Niu

Imitation learning is a promising approach for training autonomous vehicles (AV) to navigate complex traffic environments by mimicking expert driver behaviors. While existing imitation learning frameworks focus on leveraging expert…

Robotics · Computer Science 2025-09-25 Yasin Sonmez , Hanna Krasowski , Murat Arcak

When applying imitation learning techniques to fit a policy from expert demonstrations, one can take advantage of prior stability/robustness assumptions on the expert's policy and incorporate such control-theoretic prior knowledge…

Optimization and Control · Mathematics 2021-03-25 Aaron Havens , Bin Hu

We study the problem of learning similarity by using nonlinear embedding models (e.g., neural networks) from all possible pairs. This problem is well-known for its difficulty of training with the extreme number of pairs. For the special…

Machine Learning · Statistics 2021-06-16 Bowen Yuan , Yu-Sheng Li , Pengrui Quan , Chih-Jen Lin

Image retrieval is the task of finding images in a database that are most similar to a given query image. The performance of an image retrieval pipeline depends on many training-time factors, including the embedding model architecture, loss…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Gabriele Berton , Kevin Musgrave , Carlo Masone

Offline Reinforcement Learning (RL) algorithms learn a policy using a fixed training dataset, which is then deployed online to interact with the environment and make decisions. Transformers, a standard choice for modeling time-series data,…

Artificial Intelligence · Computer Science 2025-02-18 Dan Elbaz , Oren Salzman

Supervised learning is ubiquitous in medical image analysis. In this paper we consider the problem of meta-learning -- predicting which methods will perform well in an unseen classification problem, given previous experience with other…

Computer Vision and Pattern Recognition · Computer Science 2017-06-13 Veronika Cheplygina , Pim Moeskops , Mitko Veta , Behdad Dasht Bozorg , Josien Pluim

Label smoothing is ubiquitously applied in Neural Machine Translation (NMT) training. While label smoothing offers a desired regularization effect during model training, in this paper we demonstrate that it nevertheless introduces length…

Computation and Language · Computer Science 2022-05-03 Bowen Liang , Pidong Wang , Yuan Cao

Providing expert trajectories in the context of Imitation Learning is often expensive and time-consuming. The goal must therefore be to create algorithms which require as little expert data as possible. In this paper we present an algorithm…

Machine Learning · Computer Science 2022-06-14 Jonas Nüßlein , Steffen Illium , Robert Müller , Thomas Gabor , Claudia Linnhoff-Popien

Independently trained machine learning models tend to learn similar features. Given an ensemble of independently trained models, this results in correlated predictions and common failure modes. Previous attempts focusing on decorrelation of…

Unstructured environments are difficult for autonomous driving. This is because various unknown obstacles are lied in drivable space without lanes, and its width and curvature change widely. In such complex environments, searching for a…

Robotics · Computer Science 2022-02-22 Joonwoo Ahn , Minsoo Kim , Jaeheung Park

In NMT we search for the mode of the model distribution to form predictions. The mode and other high-probability translations found by beam search have been shown to often be inadequate in a number of ways. This prevents improving…

Computation and Language · Computer Science 2022-10-26 Bryan Eikema , Wilker Aziz

When an object detector is deployed in a novel setting it often experiences a drop in performance. This paper studies how an embodied agent can automatically fine-tune a pre-existing object detector while exploring and acquiring images in a…

Computer Vision and Pattern Recognition · Computer Science 2024-07-31 Gianluca Scarpellini , Stefano Rosa , Pietro Morerio , Lorenzo Natale , Alessio Del Bue

In 5G, beam training consists of the efficient association of users to beams for a given beamforming codebook used at the base station and the given propagation environment in the cell. We propose a convolutional neural network approach…

Signal Processing · Electrical Eng. & Systems 2025-10-21 Fabian Jaensch , Giuseppe Caire , Begüm Demir

Imitation learning enables robots to learn from demonstrations. Previous imitation learning algorithms usually assume access to optimal expert demonstrations. However, in many real-world applications, this assumption is limiting. Most…

Machine Learning · Computer Science 2021-03-11 Zhangjie Cao , Dorsa Sadigh

Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. This *strictly batch…

Machine Learning · Statistics 2021-01-15 Daniel Jarrett , Ioana Bica , Mihaela van der Schaar

Machine language acquisition is often presented as a problem of imitation learning: there exists a community of language users from which a learner observes speech acts and attempts to decode the mappings between utterances and situations.…

Machine Learning · Computer Science 2025-08-20 Dylan Cope , Peter McBurney