English
Related papers

Related papers: Increasing the Action Gap: New Operators for Reinf…

200 papers

This article introduces the theory of offline reinforcement learning in large state spaces, where good policies are learned from historical data without online interactions with the environment. Key concepts introduced include expressivity…

Machine Learning · Computer Science 2025-10-07 Nan Jiang , Tengyang Xie

Value function estimation is an important task in reinforcement learning, i.e., prediction. The Boltzmann softmax operator is a natural value estimator and can provide several benefits. However, it does not satisfy the non-expansion…

Machine Learning · Computer Science 2019-09-10 Ling Pan , Qingpeng Cai , Qi Meng , Wei Chen , Longbo Huang , Tie-Yan Liu

Off-policy reinforcement learning aims to leverage experience collected from prior policies for sample-efficient learning. However, in practice, commonly used off-policy approximate dynamic programming methods based on Q-learning and…

Machine Learning · Computer Science 2019-11-26 Aviral Kumar , Justin Fu , George Tucker , Sergey Levine

The choice of the control frequency of a system has a relevant impact on the ability of reinforcement learning algorithms to learn a highly performing policy. In this paper, we introduce the notion of action persistence that consists in the…

Machine Learning · Computer Science 2020-07-14 Alberto Maria Metelli , Flavio Mazzolini , Lorenzo Bisi , Luca Sabbioni , Marcello Restelli

It is well known that the extension of Watkins' algorithm to general function approximation settings is challenging: does the projected Bellman equation have a solution? If so, is the solution useful in the sense of generating a good…

Optimization and Control · Mathematics 2020-08-11 Prashant G. Mehta , Sean P. Meyn

Continuous-time stochastic processes underlie many natural and engineered systems. In healthcare, autonomous driving, and industrial control, direct interaction with the environment is often unsafe or impractical, motivating offline…

Machine Learning · Statistics 2025-11-14 Nicolas Hoischen , Petar Bevanda , Max Beier , Stefan Sosnowski , Boris Houska , Sandra Hirche

In reinforcement learning, an agent interacts sequentially with an environment to maximize a reward, receiving only partial, probabilistic feedback. This creates a fundamental exploration-exploitation trade-off: the agent must explore to…

Quantum Physics · Physics 2026-03-27 Josep Lumbreras , Ruo Cheng Huang , Yanglin Hu , Marco Fanizza , Mile Gu

We propose a novel distributionally robust $Q$-learning algorithm for the non-tabular case accounting for continuous state spaces where the state transition of the underlying Markov decision process is subject to model uncertainty. The…

Machine Learning · Computer Science 2025-05-27 Chung I Lu , Julian Sester , Aijia Zhang

In recent work it is shown that Q-learning with linear function approximation is stable, in the sense of bounded parameter estimates, under the $(\varepsilon,\kappa)$-tamed Gibbs policy; $\kappa$ is inverse temperature, and $\varepsilon>0$…

Machine Learning · Computer Science 2026-02-09 Prashant Mehta , Sean Meyn

Offline reinforcement learning leverages large datasets to train policies without interactions with the environment. The learned policies may then be deployed in real-world settings where interactions are costly or dangerous. Current…

Machine Learning · Computer Science 2022-06-29 Matthias Weissenbacher , Samarth Sinha , Animesh Garg , Yoshinobu Kawahara

The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors,…

Machine Learning · Computer Science 2022-10-19 Kishan Panaganti , Zaiyan Xu , Dileep Kalathil , Mohammad Ghavamzadeh

The analysis of Temporal Difference (TD) learning in the average-reward setting faces notable theoretical difficulties because the Bellman operator is not contractive with respect to any norm. This complicates standard analyses of…

Machine Learning · Computer Science 2026-05-05 Haoxing Tian , Zaiwei Chen , Ioannis Ch. Paschalidis , Alex Olshevsky

Guided exploration with expert demonstrations improves data efficiency for reinforcement learning, but current algorithms often overuse expert information. We propose a novel algorithm to speed up Q-learning with the help of a limited…

Machine Learning · Computer Science 2022-10-06 Fengdi Che , Xiru Zhu , Doina Precup , David Meger , Gregory Dudek

Consider a Markov decision process (MDP) that admits a set of state-action features, which can linearly express the process's probabilistic transition model. We propose a parametric Q-learning algorithm that finds an approximate-optimal…

Machine Learning · Computer Science 2019-06-07 Lin F. Yang , Mengdi Wang

Reinforcement learning has driven impressive advances in machine learning. Simultaneously, quantum-enhanced machine learning algorithms using quantum annealing underlie heavy developments. Recently, a multi-agent reinforcement learning…

Artificial Intelligence · Computer Science 2021-11-23 Tobias Müller , Christoph Roch , Kyrill Schmid , Philipp Altmann

Efficient exploration remains a challenging research problem in reinforcement learning, especially when an environment contains large state spaces, deceptive local optima, or sparse rewards. To tackle this problem, we present a…

Artificial Intelligence · Computer Science 2018-10-30 Zhang-Wei Hong , Tzu-Yun Shann , Shih-Yang Su , Yi-Hsiang Chang , Chun-Yi Lee

Q-value iteration (Q-VI) is usually analyzed through the \(\gamma\)-contraction of the Bellman operator. This argument proves convergence to \(Q^*\), but it gives only a coarse account of when the induced greedy policy becomes optimal. We…

Optimization and Control · Mathematics 2026-05-06 Donghwan Lee

Deep reinforcement learning has been shown to be a powerful framework for learning policies from complex high-dimensional sensory inputs to actions in complex tasks, such as the Atari domain. In this paper, we explore output representation…

Machine Learning · Computer Science 2016-06-16 Ishan P. Durugkar , Clemens Rosenbaum , Stefan Dernbach , Sridhar Mahadevan

In deterministic systems, reinforcement learning-based online approximate optimal control methods typically require a restrictive persistence of excitation (PE) condition for convergence. This paper presents a concurrent learning-based…

Systems and Control · Computer Science 2017-07-25 Rushikesh Kamalapurkar , Patrick Walters , Warren Dixon

Offline reinforcement learning (RL) suffers from extrapolation errors induced by out-of-distribution (OOD) actions. To address this, offline RL algorithms typically impose constraints on action selection, which can be systematically…

Machine Learning · Computer Science 2025-11-05 Yixiu Mao , Yun Qu , Qi Wang , Xiangyang Ji