English
Related papers

Related papers: Bellman Calibration for $V$-Learning in Offline Re…

200 papers

We present and analyze the Krylov-Bellman Boosting (KBB) algorithm for policy evaluation in general state spaces. It alternates between fitting the Bellman residual using non-parametric regression (as in boosting), and estimating the value…

Machine Learning · Statistics 2023-03-28 Eric Xia , Martin J. Wainwright

Machine learning classifiers are probabilistic in nature, and thus inevitably involve uncertainty. Predicting the probability of a specific input to be correct is called uncertainty (or confidence) estimation and is crucial for risk…

Machine Learning · Computer Science 2023-01-11 Gabriella Chouraqui , Liron Cohen , Gil Einziger , Liel Leman

Probability predictions from binary regressions or machine learning methods ought to be calibrated: If an event is predicted to occur with probability $x$, it should materialize with approximately that frequency, which means that the…

Statistics Theory · Mathematics 2023-01-11 Timo Dimitriadis , Lutz Duembgen , Alexander Henzi , Marius Puke , Johanna Ziegel

A key problem in off-policy Reinforcement Learning (RL) is the mismatch, or distribution shift, between the dataset and the distribution over states and actions visited by the learned policy. This problem is exacerbated in the fully offline…

Machine Learning · Computer Science 2023-11-28 Melrose Roderick , Gaurav Manek , Felix Berkenkamp , J. Zico Kolter

Offline reinforcement learning (RL) is a variant of RL where the policy is learned from a previously collected dataset of trajectories and rewards. In our work, we propose a practical approach to offline RL with large language models…

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

Machine Learning · Computer Science 2025-03-18 Natinael Solomon Neggatu , Jeremie Houssineau , Giovanni Montana

Proper confidence calibration of deep neural networks is essential for reliable predictions in safety-critical tasks. Miscalibration can lead to model over-confidence and/or under-confidence; i.e., the model's confidence in its prediction…

Machine Learning · Computer Science 2023-08-08 Shuang Ao , Stefan Rueger , Advaith Siddharthan

Online continual learning (OCL), which enables AI systems to adaptively learn from non-stationary data streams, is commonly achieved using experience replay (ER)-based methods that retain knowledge by replaying stored past during training.…

Machine Learning · Computer Science 2025-02-26 Zelin Tao , Hao Deng , Mingqing Liu , Lijun Zhang , Shengjie Zhao

We consider a challenging theoretical problem in offline reinforcement learning (RL): obtaining sample-efficiency guarantees with a dataset lacking sufficient coverage, under only realizability-type assumptions for the function…

Machine Learning · Computer Science 2022-06-16 Jinglin Chen , Nan Jiang

Offline reinforcement learning learns policies from fixed datasets without further environment interaction. A key challenge in this setting is epistemic uncertainty, arising from limited or biased data coverage, particularly when the…

Machine Learning · Computer Science 2026-04-09 Abhilash Reddy Chenreddy , Erick Delage

Reinforcement learning (RL) algorithms still suffer from high sample complexity despite outstanding recent successes. The need for intensive interactions with the environment is especially observed in many widely popular policy gradient…

Machine Learning · Computer Science 2020-08-04 Samuele Tosatto , Joao Carvalho , Hany Abdulsamad , Jan Peters

In deep Reinforcement Learning (RL), value functions are typically approximated using deep neural networks and trained via mean squared error regression objectives to fit the true value functions. Recent research has proposed an alternative…

Machine Learning · Computer Science 2024-11-19 Denis Tarasov , Kirill Brilliantov , Dmitrii Kharlapenko

Deep neural networks often produce miscalibrated probability estimates, leading to overconfident predictions. A common approach for calibration is fitting a post-hoc calibration map on unseen validation data that transforms predicted…

Machine Learning · Computer Science 2025-07-10 Yunrui Zhang , Gustavo Batista , Salil S. Kanhere

We study finite-horizon continuous-time policy evaluation from discrete closed-loop trajectories under time-inhomogeneous dynamics. The target value surface solves a backward parabolic equation, but the Bellman baseline obtained from…

Machine Learning · Statistics 2026-05-11 Yaowei Zheng , Richong Zhang , Shenxi Wu , Shirui Bian , Haosong Zhang , Li Zeng , Xingjian Ma , Yichi Zhang

Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcement learning perspective, where the goal is to learn the…

Machine Learning · Computer Science 2024-09-04 Carlos E. Luis , Alessandro G. Bottero , Julia Vinogradska , Felix Berkenkamp , Jan Peters

In the recent literature on machine learning and decision making, calibration has emerged as a desirable and widely-studied statistical property of the outputs of binary prediction models. However, the algorithmic aspects of measuring model…

Machine Learning · Computer Science 2024-06-24 Lunjia Hu , Arun Jambulapati , Kevin Tian , Chutong Yang

Offline reinforcement learning (RL) defines the task of learning from a fixed batch of data. Due to errors in value estimation from out-of-distribution actions, most offline RL algorithms take the approach of constraining or regularizing…

Machine Learning · Computer Science 2021-12-06 Scott Fujimoto , Shixiang Shane Gu

Recently, there has been a surge of interest in analyzing the non-asymptotic behavior of model-free reinforcement learning algorithms. However, the performance of such algorithms in non-ideal environments, such as in the presence of…

Machine Learning · Computer Science 2024-09-06 Sreejeet Maity , Aritra Mitra

Reinforcement learning (RL) is increasingly used to align large language models (LLMs). Off-policy methods offer greater implementation simplicity and data efficiency than on-policy techniques, but often result in suboptimal performance. In…

Machine Learning · Computer Science 2025-12-01 Charles Arnal , Gaëtan Narozniak , Vivien Cabannes , Yunhao Tang , Julia Kempe , Remi Munos

Calibration is crucial in deep learning applications, especially in fields like healthcare and autonomous driving, where accurate confidence estimates are vital for decision-making. However, deep neural networks often suffer from…

Machine Learning · Computer Science 2024-10-17 Linwei Tao , Haolan Guo , Minjing Dong , Chang Xu