English
Related papers

Related papers: Disentangling Recognition and Decision Regrets in …

200 papers

Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach.…

Machine Learning · Computer Science 2020-08-04 Timo P. Gros , Daniel Höller , Jörg Hoffmann , Verena Wolf

Probabilistic classifiers are central for making informed decisions under uncertainty. Based on the maximum expected utility principle, optimal decision rules can be derived using the posterior class probabilities and misclassification…

Machine Learning · Computer Science 2025-03-25 Alexandre Perez-Lebel , Gael Varoquaux , Sanmi Koyejo , Matthieu Doutreligne , Marine Le Morvan

Assuming unknown classes could be present during classification, the open set recognition (OSR) task aims to classify an instance into a known class or reject it as unknown. In this paper, we use a two-stage training strategy for the OSR…

Computer Vision and Pattern Recognition · Computer Science 2022-09-30 Jingyun Jia , Philip K. Chan

Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space). Visual domain randomisation encourages transfer…

Artificial Intelligence · Computer Science 2021-01-12 Sasha Salter , Dushyant Rao , Markus Wulfmeier , Raia Hadsell , Ingmar Posner

The concepts of overfitting and generalization are vital for evaluating machine learning models. In this work, we show that the popular Recall@K metric depends on the number of classes in the dataset, which limits its ability to estimate…

Machine Learning · Computer Science 2023-06-26 Maksim Zhdanov , Ivan Karpukhin

Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generation models, which uses reward functions to enhance generation quality and human preference…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Yunqi Hong , Kuei-Chun Kao , Hengguang Zhou , Cho-Jui Hsieh

A primary challenge for visual-based Reinforcement Learning (RL) is to generalize effectively across unseen environments. Although previous studies have explored different auxiliary tasks to enhance generalization, few adopt image…

Computer Vision and Pattern Recognition · Computer Science 2024-10-16 Di Zhang , Bowen Lv , Hai Zhang , Feifan Yang , Junqiao Zhao , Hang Yu , Chang Huang , Hongtu Zhou , Chen Ye , Changjun Jiang

When robots learn reward functions using high capacity models that take raw state directly as input, they need to both learn a representation for what matters in the task -- the task ``features" -- as well as how to combine these features…

Robotics · Computer Science 2023-03-20 Andreea Bobu , Yi Liu , Rohin Shah , Daniel S. Brown , Anca D. Dragan

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

Residual reinforcement learning (RL) has been proposed as a way to solve challenging robotic tasks by adapting control actions from a conventional feedback controller to maximize a reward signal. We extend the residual formulation to learn…

Machine Learning · Computer Science 2021-06-16 Minttu Alakuijala , Gabriel Dulac-Arnold , Julien Mairal , Jean Ponce , Cordelia Schmid

We study the regret of reinforcement learning from offline data generated by a fixed behavior policy in an infinite-horizon discounted Markov decision process (MDP). While existing analyses of common approaches, such as fitted $Q$-iteration…

Machine Learning · Computer Science 2023-07-13 Yichun Hu , Nathan Kallus , Masatoshi Uehara

This position paper proposes a fresh look at Reinforcement Learning (RL) from the perspective of data-efficiency. Data-efficient RL has gone through three major stages: pure on-line RL where every data-point is considered only once, RL with…

Machine Learning · Computer Science 2021-08-24 Martin Riedmiller , Jost Tobias Springenberg , Roland Hafner , Nicolas Heess

We study tabular reinforcement learning problems with multiple steps of lookahead information. Before acting, the learner observes $\ell$ steps of future transition and reward realizations: the exact state the agent would reach and the…

Machine Learning · Computer Science 2026-01-16 Nadav Merlis

Despite being able to capture a range of features of the data, high accuracy models trained with supervision tend to make similar predictions. This seemingly implies that high-performing models share similar biases regardless of training…

Machine Learning · Computer Science 2022-04-27 Raphael Gontijo-Lopes , Yann Dauphin , Ekin D. Cubuk

Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provide a succinct and causal description of the world, and many…

Machine Learning · Computer Science 2021-06-07 William Agnew , Pedro Domingos

Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-world objectives--especially those derived from human preferences--are often uncertain,…

Machine Learning · Computer Science 2026-04-30 Disha Singha

Recent disentangled representation learning (DRL) methods heavily rely on factor specific strategies-either learning objectives for attributes or model architectures for objects-to embed inductive biases. Such divergent approaches result in…

Machine Learning · Computer Science 2025-11-12 Whie Jung , Dong Hoon Lee , Seunghoon Hong

Supervised fine-tuning (SFT) is a common first stage of LLM post-training, teaching the model to follow instructions and shaping its behavior as a helpful assistant. At the same time, SFT may harm the fundamental capabilities of an LLM,…

Machine Learning · Computer Science 2026-04-16 Mark Rofin , Aditya Varre , Nicolas Flammarion

Recent advances at the intersection of reinforcement learning (RL) and visual intelligence have enabled agents that not only perceive complex visual scenes but also reason, generate, and act within them. This survey offers a critical and…

Computer Vision and Pattern Recognition · Computer Science 2025-12-24 Weijia Wu , Chen Gao , Joya Chen , Kevin Qinghong Lin , Qingwei Meng , Yiming Zhang , Yuke Qiu , Hong Zhou , Mike Zheng Shou

This paper deals with optimal policy learning (OPL) with observational data, i.e. data-driven optimal decision-making, in multi-action (or multi-arm) settings, where a finite set of decision options is available. It is organized in three…

Machine Learning · Statistics 2024-04-01 Giovanni Cerulli