English
Related papers

Related papers: Guarantees for Epsilon-Greedy Reinforcement Learni…

200 papers

We study the policy evaluation problem in an online multi-reward multi-policy discounted setting, where multiple reward functions must be evaluated simultaneously for different policies. We adopt an $(\epsilon,\delta)$-PAC perspective to…

Machine Learning · Computer Science 2025-08-19 Alessio Russo , Aldo Pacchiano

Intrinsic rewards play a central role in handling the exploration-exploitation trade-off when designing sequential decision-making algorithms, in both foundational theory and state-of-the-art deep reinforcement learning. The LinUCB…

Machine Learning · Computer Science 2022-04-13 Jordan T. Ash , Cyril Zhang , Surbhi Goel , Akshay Krishnamurthy , Sham Kakade

A key challenge in applying reinforcement learning to safety-critical domains is understanding how to balance exploration (needed to attain good performance on the task) with safety (needed to avoid catastrophic failure). Although a growing…

Machine Learning · Computer Science 2021-03-23 Melrose Roderick , Vaishnavh Nagarajan , J. Zico Kolter

In many real-world applications of reinforcement learning (RL), deployed policies have varied impacts on different stakeholders, creating challenges in reaching consensus on how to effectively aggregate their preferences. Generalized…

Machine Learning · Computer Science 2025-07-17 Cheol Woo Kim , Jai Moondra , Shresth Verma , Madeleine Pollack , Lingkai Kong , Milind Tambe , Swati Gupta

We initiate the study of multi-stage episodic reinforcement learning under adversarial corruptions in both the rewards and the transition probabilities of the underlying system extending recent results for the special case of stochastic…

Machine Learning · Computer Science 2023-11-02 Thodoris Lykouris , Max Simchowitz , Aleksandrs Slivkins , Wen Sun

Safe reinforcement learning has been a promising approach for optimizing the policy of an agent that operates in safety-critical applications. In this paper, we propose an algorithm, SNO-MDP, that explores and optimizes Markov decision…

Machine Learning · Computer Science 2020-08-18 Akifumi Wachi , Yanan Sui

Behavior of the entropy numbers of classes of multivariate functions with mixed smoothness is studied here. This problem has a long history and some fundamental problems in the area are still open. The main goal of this paper is to develop…

Numerical Analysis · Mathematics 2016-03-01 V. Temlyakov

While standard reinforcement learning optimizes a single reward signal, many applications require optimizing a nonlinear utility $f(J_1^\pi,\dots,J_M^\pi)$ over multiple objectives, where each $J_m^\pi$ denotes the expected discounted…

Machine Learning · Computer Science 2026-03-10 Swetha Ganesh , Vaneet Aggarwal

Reinforcement learning has recently gained traction as a means to improve combinatorial optimization methods, yet its effectiveness within local search metaheuristics specifically remains comparatively underexamined. In this study, we…

Machine Learning · Computer Science 2026-01-14 Yannick Molinghen , Augustin Delecluse , Renaud De Landtsheer , Stefano Michelini

High sample complexity remains a barrier to the application of reinforcement learning (RL), particularly in multi-agent systems. A large body of work has demonstrated that exploration mechanisms based on the principle of optimism under…

Machine Learning · Computer Science 2021-08-02 Robert Loftin , Aadirupa Saha , Sam Devlin , Katja Hofmann

Robust Markov decision processes (MDPs) provide a general framework to model decision problems where the system dynamics are changing or only partially known. Efficient methods for some \texttt{sa}-rectangular robust MDPs exist, using its…

Artificial Intelligence · Computer Science 2022-10-06 Navdeep Kumar , Kfir Levy , Kaixin Wang , Shie Mannor

We study reinforcement learning from human feedback in general Markov decision processes, where agents learn from trajectory-level preference comparisons. A central challenge in this setting is to design algorithms that select informative…

Machine Learning · Computer Science 2025-12-05 Andreas Schlaginhaufen , Reda Ouhamma , Maryam Kamgarpour

Policy optimization methods are popular reinforcement learning algorithms, because their incremental and on-policy nature makes them more stable than the value-based counterparts. However, the same properties also make them slow to converge…

Machine Learning · Computer Science 2021-07-01 Andrea Zanette , Ching-An Cheng , Alekh Agarwal

Exploration strategies in continuous action space are often heuristic due to the infinite actions, and these kinds of methods cannot derive a general conclusion. In prior work, it has been shown that policy-based exploration is beneficial…

Machine Learning · Computer Science 2023-08-23 Xing Chen , Yijun Liu , Zhaogeng Liu , Hechang Chen , Hengshuai Yao , Yi Chang

We consider large-scale Markov decision processes (MDPs) with an unknown cost function and employ stochastic convex optimization tools to address the problem of imitation learning, which consists of learning a policy from a finite set of…

Machine Learning · Computer Science 2022-01-04 Angeliki Kamoutsi , Goran Banjac , John Lygeros

General-purpose, intelligent, learning agents cycle through sequences of observations, actions, and rewards that are complex, uncertain, unknown, and non-Markovian. On the other hand, reinforcement learning is well-developed for small…

Machine Learning · Computer Science 2009-12-30 Marcus Hutter

We study a finite-horizon restless multi-armed bandit problem with multiple actions, dubbed R(MA)^2B. The state of each arm evolves according to a controlled Markov decision process (MDP), and the reward of pulling an arm depends on both…

Machine Learning · Computer Science 2022-03-25 Guojun Xiong , Jian Li , Rahul Singh

Motivated by many application problems, we consider Markov decision processes (MDPs) with a general loss function and unknown parameters. To mitigate the epistemic uncertainty associated with unknown parameters, we take a Bayesian approach…

Machine Learning · Computer Science 2025-10-02 Xiaoshuang Wang , Yifan Lin , Enlu Zhou

In order to compute near-optimal policies with policy-gradient algorithms, it is common in practice to include intrinsic exploration terms in the learning objective. Although the effectiveness of these terms is usually justified by an…

Machine Learning · Computer Science 2025-08-21 Adrien Bolland , Gaspard Lambrechts , Damien Ernst

Despite empirical success, the theory of reinforcement learning (RL) with value function approximation remains fundamentally incomplete. Prior work has identified a variety of pathological behaviours that arise in RL algorithms that combine…

Machine Learning · Computer Science 2020-10-30 Kenny Young , Richard S. Sutton