English
Related papers

Related papers: Policy Entropy for Out-of-Distribution Classificat…

200 papers

Reinforcement learning (RL) is one of the most vibrant research frontiers in machine learning and has been recently applied to solve a number of challenging problems. In this paper, we primarily focus on off-policy evaluation (OPE), one of…

Machine Learning · Statistics 2022-12-14 Masatoshi Uehara , Chengchun Shi , Nathan Kallus

Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative…

Machine Learning · Computer Science 2026-03-13 Aleksei Petrenko , Ben Lipkin , Kevin Chen , Erik Wijmans , Marco Cusumano-Towner , Raja Giryes , Philipp Krähenbühl

Deep learning systems frequently fail at out-of-context (OOC) prediction, the problem of making reliable predictions on uncommon or unusual inputs or subgroups of the training distribution. To this end, a number of benchmarks for measuring…

Machine Learning · Computer Science 2021-10-27 David Madras , Richard Zemel

Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…

Score-function based methods for policy learning, such as REINFORCE and PPO, have delivered strong results in game-playing and robotics, yet their high variance often undermines training stability. Using pathwise policy gradients, i.e.…

Modern neural networks are very powerful predictive models, but they are often incapable of recognizing when their predictions may be wrong. Closely related to this is the task of out-of-distribution detection, where a network must…

Machine Learning · Statistics 2018-02-15 Terrance DeVries , Graham W. Taylor

Reinforcement Learning (RL) has been shown effective in domains where the agent can learn policies by actively interacting with its operating environment. However, if we change the RL scheme to offline setting where the agent can only…

Machine Learning · Computer Science 2021-11-11 Jinning Li , Chen Tang , Masayoshi Tomizuka , Wei Zhan

Detecting out-of-distribution (OOD) samples is essential when deploying machine learning models in open-world scenarios. Zero-shot OOD detection, requiring no training on in-distribution (ID) data, has been possible with the advent of…

Machine Learning · Computer Science 2024-06-04 Chentao Cao , Zhun Zhong , Zhanke Zhou , Yang Liu , Tongliang Liu , Bo Han

Compared to on-policy counterparts, off-policy model-free deep reinforcement learning can improve data efficiency by repeatedly using the previously gathered data. However, off-policy learning becomes challenging when the discrepancy…

Machine Learning · Computer Science 2023-09-27 Baturay Saglam , Dogan C. Cicek , Furkan B. Mutlu , Suleyman S. Kozat

There is an increasing need to determine whether inputs are out-of-distribution (\emph{OOD}) for safely deploying machine learning models in the open world scenario. Typical neural classifiers are based on the closed world assumption, where…

Computer Vision and Pattern Recognition · Computer Science 2022-08-15 Sen Pei , Xin Zhang , Bin Fan , Gaofeng Meng

Reinforcement learning (RL) has achieved remarkable success in fields like robotics and autonomous driving, but adversarial attacks designed to mislead RL systems remain challenging. Existing approaches often rely on modifying the…

Machine Learning · Computer Science 2025-07-25 Junyong Jiang , Buwei Tian , Chenxing Xu , Songze Li , Lu Dong

Deep Neural Networks for classification behave unpredictably when confronted with inputs not stemming from the training distribution. This motivates out-of-distribution detection (OOD) mechanisms. The usual lack of prior information on…

Machine Learning · Computer Science 2022-03-02 Konstantin Kirchheim , Tim Gonschorek , Frank Ortmeier

Optimal decision making with limited or no information in stochastic environments where multiple agents interact is a challenging topic in the realm of artificial intelligence. Reinforcement learning (RL) is a popular approach for arriving…

Machine Learning · Computer Science 2019-01-08 Roi Ceren

Refraining from confidently predicting when faced with categories of inputs different from those seen during training is an important requirement for the safe deployment of deep learning systems. While simple to state, this has been a…

Machine Learning · Computer Science 2021-05-18 Sunil Thulasidasan , Sushil Thapa , Sayera Dhaubhadel , Gopinath Chennupati , Tanmoy Bhattacharya , Jeff Bilmes

Recent work has shown that deep generative models can assign higher likelihood to out-of-distribution data sets than to their training data (Nalisnick et al., 2019; Choi et al., 2019). We posit that this phenomenon is caused by a mismatch…

Machine Learning · Statistics 2019-10-17 Eric Nalisnick , Akihiro Matsukawa , Yee Whye Teh , Balaji Lakshminarayanan

We consider the problem of modeling trajectories of drivers in a road network from the perspective of inverse reinforcement learning. Cars are detected by sensors placed on sparsely distributed points on the street network of a city. As…

Artificial Intelligence · Computer Science 2024-01-22 Anselmo R. Pitombeira-Neto , Helano P. Santos , Ticiana L. Coelho da Silva , José Antonio F. de Macedo

Off-policy learning is a framework for optimizing policies without deploying them, using data collected by another policy. In recommender systems, this is especially challenging due to the imbalance in logged data: some items are…

Machine Learning · Computer Science 2024-10-23 Matej Cief , Branislav Kveton , Michal Kompan

This paper proposes an observer-based framework for solving Partially Observable Markov Decision Processes (POMDPs) when an accurate model is not available. We first propose to use a Moving Horizon Estimation-Model Predictive Control…

Systems and Control · Electrical Eng. & Systems 2021-03-23 Hossein Nejatbakhsh Esfahani , Arash Bahari Kordabad , Sebastien Gros

Deep Neural Networks are powerful models that attained remarkable results on a variety of tasks. These models are shown to be extremely efficient when training and test data are drawn from the same distribution. However, it is not clear how…

Machine Learning · Statistics 2019-01-11 Gabi Shalev , Yossi Adi , Joseph Keshet

Simplicity is a critical inductive bias for designing data-driven controllers, especially when robustness is important. Despite the impressive results of deep reinforcement learning in complex control tasks, it is prone to capturing…

Machine Learning · Computer Science 2025-05-09 Bang You , Chenxu Wang , Huaping Liu