English
Related papers

Related papers: Learning structured data from unspecific reinforce…

200 papers

Real-world reinforcement learning applications are often hindered by delayed feedback from environments, which violates the Markov assumption and introduces significant challenges. Although numerous delay-compensating methods have been…

Machine Learning · Computer Science 2026-02-03 Jongsoo Lee , Jangwon Kim , Jiseok Jeong , Soohee Han

A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes. We propose a natural constraint on exploration -- \textit{uniformly} outperforming a conservative policy…

Machine Learning · Computer Science 2023-02-27 Wanqiao Xu , Jason Yecheng Ma , Kan Xu , Hamsa Bastani , Osbert Bastani

This paper introduces Fast Linearized Adaptive Policy (FLAP), a new meta-reinforcement learning (meta-RL) method that is able to extrapolate well to out-of-distribution tasks without the need to reuse data from training, and adapt almost…

Machine Learning · Computer Science 2021-01-14 Matt Peng , Banghua Zhu , Jiantao Jiao

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

Machine Learning · Computer Science 2020-10-14 Heinrich Jiang , Qijia Jiang , Aldo Pacchiano

Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumptions on the problem data, they can exhibit the slow…

Optimization and Control · Mathematics 2026-05-18 Jeremy Bertoncini , Alberto De Marchi , Matthias Gerdts , Simon Gottschalk

When trained on diverse labeled data, machine learning models have proven themselves to be a powerful tool in all facets of society. However, due to budget limitations, deliberate or non-deliberate censorship, and other problems during data…

Machine Learning · Statistics 2022-03-25 Thomas Kehrenberg , Myles Bartlett , Viktoriia Sharmanska , Novi Quadrianto

This paper discusses a system that accelerates reinforcement learning by using transfer from related tasks. Without such transfer, even if two tasks are very similar at some abstract level, an extensive re-learning effort is required. The…

Artificial Intelligence · Computer Science 2011-06-10 C. Drummond

When the agent's observations or interactions are delayed, classic reinforcement learning tools usually fail. In this paper, we propose a simple yet new and efficient solution to this problem. We assume that, in the undelayed environment,…

Machine Learning · Computer Science 2022-05-12 Pierre Liotet , Davide Maran , Lorenzo Bisi , Marcello Restelli

We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data. In particular, we face the case where some attributes (bias) of the data, if learned by the model, can severely…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Ruggero Ragonesi , Riccardo Volpi , Jacopo Cavazza , Vittorio Murino

The prototypical approach to reinforcement learning involves training policies tailored to a particular agent from scratch for every new morphology. Recent work aims to eliminate the re-training of policies by investigating whether a…

Machine Learning · Computer Science 2022-06-27 Brandon Trabucco , Mariano Phielipp , Glen Berseth

Compositional generalization, the ability of an agent to generalize to unseen combinations of latent factors, is easy for humans but hard for deep neural networks. A line of research in cognitive science has hypothesized a process,…

Machine Learning · Computer Science 2023-10-31 Yi Ren , Samuel Lavoie , Mikhail Galkin , Danica J. Sutherland , Aaron Courville

Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies. However, methods that use pure reinforcement learning with simple reward functions tend to produce…

Robotics · Computer Science 2017-07-11 Josh Merel , Yuval Tassa , Dhruva TB , Sriram Srinivasan , Jay Lemmon , Ziyu Wang , Greg Wayne , Nicolas Heess

Learning controllable and generalizable representation of multivariate data with desired structural properties remains a fundamental problem in machine learning. In this paper, we present a novel framework for learning generative models…

Machine Learning · Computer Science 2020-10-05 Ruixiang Zhang , Masanori Koyama , Katsuhiko Ishiguro

In many real-world scenarios, labeled data for a specific machine learning task is costly to obtain. Semi-supervised training methods make use of abundantly available unlabeled data and a smaller number of labeled examples. We propose a new…

Computer Vision and Pattern Recognition · Computer Science 2017-06-06 Philip Häusser , Alexander Mordvintsev , Daniel Cremers

Constraint-based learning reduces the burden of collecting labels by having users specify general properties of structured outputs, such as constraints imposed by physical laws. We propose a novel framework for simultaneously learning these…

Machine Learning · Computer Science 2018-06-01 Hongyu Ren , Russell Stewart , Jiaming Song , Volodymyr Kuleshov , Stefano Ermon

In this paper, we present an approach based on reinforcement learning for eye tracking data manipulation. It is based on two opposing agents, where one tries to classify the data correctly and the second agent looks for patterns in the…

Machine Learning · Computer Science 2020-10-05 Wolfgang Fuhl , Efe Bozkir , Enkelejda Kasneci

Reinforcement learning systems have the potential to enable continuous improvement in unstructured environments, leveraging data collected autonomously. However, in practice these systems require significant amounts of instrumentation or…

Robotics · Computer Science 2022-03-30 Abhishek Gupta , Corey Lynch , Brandon Kinman , Garrett Peake , Sergey Levine , Karol Hausman

We propose a novel reinforcement learning-based approach for adaptive and iterative feature selection. Given a masked vector of input features, a reinforcement learning agent iteratively selects certain features to be unmasked, and uses…

Machine Learning · Computer Science 2020-05-26 Uri Shaham , Tom Zahavy , Cesar Caraballo , Shiwani Mahajan , Daisy Massey , Harlan Krumholz

Many practical applications of reinforcement learning constrain agents to learn from a fixed batch of data which has already been gathered, without offering further possibility for data collection. In this paper, we demonstrate that due to…

Machine Learning · Computer Science 2019-08-13 Scott Fujimoto , David Meger , Doina Precup

We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning. Our model learns jointly to represent data and to bind class labels to representations in a single shot. It builds…

Neural and Evolutionary Computing · Computer Science 2018-07-16 Tsendsuren Munkhdalai , Adam Trischler