English
Related papers

Related papers: Corruption-Tolerant Asynchronous Q-Learning with N…

200 papers

This work theoretically studies a ubiquitous reinforcement learning policy for controlling the canonical model of continuous-time stochastic linear-quadratic systems. We show that randomized certainty equivalent policy addresses the…

Machine Learning · Computer Science 2022-08-23 Mohamad Kazem Shirani Faradonbeh

Clinical decision-making often involves selecting tests that are costly, invasive, or time-consuming, motivating individualized, sequential strategies for what to measure and when to stop ascertaining. We study the problem of learning…

Machine Learning · Statistics 2026-04-16 Doudou Zhou , Yiran Zhang , Dian Jin , Yingye Zheng , Lu Tian , Tianxi Cai

Many real-world applications of reinforcement learning (RL) require making decisions in continuous action environments. In particular, determining the optimal dose level plays a vital role in developing medical treatment regimes. One…

Machine Learning · Statistics 2023-10-03 Yuhan Li , Wenzhuo Zhou , Ruoqing Zhu

High order momentum-based parameter update algorithms have seen widespread applications in training machine learning models. Recently, connections with variational approaches have led to the derivation of new learning algorithms with…

Optimization and Control · Mathematics 2021-06-08 Joseph E. Gaudio , Anuradha M. Annaswamy , José M. Moreu , Michael A. Bolender , Travis E. Gibson

The Zap Q-learning algorithm introduced in this paper is an improvement of Watkins' original algorithm and recent competitors in several respects. It is a matrix-gain algorithm designed so that its asymptotic variance is optimal. Moreover,…

Systems and Control · Computer Science 2018-03-23 Adithya M. Devraj , Sean P. Meyn

In finance, sequential decision problems are often faced, for which reinforcement learning (RL) emerges as a promising tool for optimisation without the need of analytical tractability. However, the objective of classical RL is the expected…

Computational Finance · Quantitative Finance 2026-02-13 Federico Cacciamani , Roberto Daluiso , Marco Pinciroli , Michele Trapletti , Edoardo Vittori

Reward modeling has emerged as a promising approach for the scalable alignment of language models. However, contemporary reward models (RMs) often lack robustness, awarding high rewards to low-quality, out-of-distribution (OOD) samples.…

This paper presents the concept of an adaptive safe padding that forces Reinforcement Learning (RL) to synthesise optimal control policies while ensuring safety during the learning process. Policies are synthesised to satisfy a goal,…

Machine Learning · Computer Science 2020-03-24 Mohammadhosein Hasanbeig , Alessandro Abate , Daniel Kroening

This paper considers the problem of solving constrained reinforcement learning problems with anytime guarantees, meaning that the algorithmic solution returns a safe policy regardless of when it is terminated. Drawing inspiration from…

Systems and Control · Electrical Eng. & Systems 2025-11-18 Pol Mestres , Arnau Marzabal , Jorge Cortés

Reinforcement learning has traditionally been studied with exponential discounting or the average reward setup, mainly due to their mathematical tractability. However, such frameworks fall short of accurately capturing human behavior, which…

Machine Learning · Computer Science 2024-09-18 S. R. Eshwar , Mayank Motwani , Nibedita Roy , Gugan Thoppe

Reinforcement learning (RL) for reachability specifications is fundamental in sequential decision-making, yet theoretical guarantees remain less explored. A recent work achieves asymptotic convergence to optimal policies. However, this…

Machine Learning · Computer Science 2026-05-26 Amogh Palasamudram , Jakub Svoboda , Suguman Bansal , Krishnendu Chatterjee

Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…

Artificial Intelligence · Computer Science 2025-11-26 Dominik Wagner , Leon Witzman , Luke Ong

Autonomous agents must often deal with conflicting requirements, such as completing tasks using the least amount of time/energy, learning multiple tasks, or dealing with multiple opponents. In the context of reinforcement learning~(RL),…

Machine Learning · Computer Science 2019-10-30 Santiago Paternain , Luiz F. O. Chamon , Miguel Calvo-Fullana , Alejandro Ribeiro

We study the stochastic multi-armed bandits problem in the presence of adversarial corruption. We present a new algorithm for this problem whose regret is nearly optimal, substantially improving upon previous work. Our algorithm is agnostic…

Machine Learning · Computer Science 2019-03-29 Anupam Gupta , Tomer Koren , Kunal Talwar

We consider the sequential optimization of an unknown, continuous, and expensive to evaluate reward function, from noisy and adversarially corrupted observed rewards. When the corruption attacks are subject to a suitable budget $C$ and the…

Machine Learning · Statistics 2022-03-30 Ilija Bogunovic , Zihan Li , Andreas Krause , Jonathan Scarlett

Existing metrics for reinforcement learning (RL) such as regret, PAC bounds, or uniform-PAC (Dann et al., 2017), typically evaluate the cumulative performance, while allowing the agent to play an arbitrarily bad policy at any finite time t.…

Machine Learning · Computer Science 2024-11-01 Junyan Liu , Yunfan Li , Ruosong Wang , Lin F. Yang

We introduce the lookahead-bounded Q-learning (LBQL) algorithm, a new, provably convergent variant of Q-learning that seeks to improve the performance of standard Q-learning in stochastic environments through the use of ``lookahead'' upper…

Machine Learning · Computer Science 2020-06-30 Ibrahim El Shar , Daniel R. Jiang

Decision making and learning in the presence of uncertainty has attracted significant attention in view of the increasing need to achieve robust and reliable operations. In the case where uncertainty stems from the presence of adversarial…

Machine Learning · Computer Science 2024-03-25 André Bertolace , Konstatinos Gatsis , Kostas Margellos

This paper is concerned with the linear quadratic optimal control of discrete-time time-varying system with terminal state constraint. The main contribution is to propose a Q-learning algorithm for the optimal controller when the…

Optimization and Control · Mathematics 2023-07-20 Juanjuan Xu , Jingmei Liu , Zhaorong Zhang , Wei Wang

We study the problem of safe offline reinforcement learning (RL), the goal is to learn a policy that maximizes long-term reward while satisfying safety constraints given only offline data, without further interaction with the environment.…

Machine Learning · Computer Science 2022-04-11 Haoran Xu , Xianyuan Zhan , Xiangyu Zhu