English
Related papers

Related papers: Safe Exploration for Efficient Policy Evaluation a…

200 papers

Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…

Machine Learning · Statistics 2024-02-20 Davide Mambelli , Stephan Bongers , Onno Zoeter , Matthijs T. J. Spaan , Frans A. Oliehoek

Information and free-energy maximization are physics principles that provide general rules for an agent to optimize actions in line with specific goals and policies. These principles are the building blocks for designing decision-making…

Machine Learning · Computer Science 2025-03-21 Alex Barbier-Chebbah , Christian L. Vestergaard , Jean-Baptiste Masson

A sensing policy for the restless multi-armed bandit problem with stationary but unknown reward distributions is proposed. The work is presented in the context of cognitive radios in which the bandit problem arises when deciding which parts…

Information Theory · Computer Science 2012-11-20 Jan Oksanen , Visa Koivunen , H. Vincent Poor

Causal graphical models can encode large amounts structural knowledge, both from the background knowledge of domain experts and the structural knowledge discovered from randomized experiments or observational data. However, though we may…

Machine Learning · Computer Science 2026-04-07 Katherine Avery , Chinmay Pendse , David Jensen

This paper establishes the equivalence between cognitive medium access and the competitive multi-armed bandit problem. First, the scenario in which a single cognitive user wishes to opportunistically exploit the availability of empty…

Information Theory · Computer Science 2007-10-09 Lifeng Lai , Hesham El Gamal , Hai Jiang , H. Vincent Poor

The multi-armed bandit problem is a core framework for sequential decision-making under uncertainty, but classical algorithms often fail in environments with hidden, time-varying states that confound reward estimation and optimal action…

Machine Learning · Computer Science 2026-02-19 Jikai Jin , Kenneth Hung , Sanath Kumar Krishnamurthy , Baoyi Shi , Congshan Zhang

We consider a scenario where an agent has multiple available strategies to explore an unknown environment. For each new interaction with the environment, the agent must select which exploration strategy to use. We provide a new…

Machine Learning · Computer Science 2018-08-24 Fabien C. Y. Benureau , Pierre-Yves Oudeyer

We study the problem of online learning in adversarial bandit problems under a partial observability model called off-policy feedback. In this sequential decision making problem, the learner cannot directly observe its rewards, but instead…

Machine Learning · Computer Science 2022-07-20 Germano Gabbianelli , Matteo Papini , Gergely Neu

We tackle the issue of finding a good policy when the number of policy updates is limited. This is done by approximating the expected policy reward as a sequence of concave lower bounds which can be efficiently maximized, drastically…

Artificial Intelligence · Computer Science 2016-12-30 Nicolas Le Roux

Multi-Armed-Bandit frameworks have often been used by researchers to assess educational interventions, however, recent work has shown that it is more beneficial for a student to provide qualitative feedback through preference elicitation…

Machine Learning · Computer Science 2021-11-02 Nayan Saxena , Pan Chen , Emmy Liu

Safe exploration presents a major challenge in reinforcement learning (RL): when active data collection requires deploying partially trained policies, we must ensure that these policies avoid catastrophically unsafe regions, while still…

Machine Learning · Computer Science 2021-04-27 Homanga Bharadhwaj , Aviral Kumar , Nicholas Rhinehart , Sergey Levine , Florian Shkurti , Animesh Garg

We consider the task of evaluating a policy for a Markov decision process (MDP). The standard unbiased technique for evaluating a policy is to deploy the policy and observe its performance. We show that the data collected from deploying a…

Artificial Intelligence · Computer Science 2017-06-13 Josiah P. Hanna , Philip S. Thomas , Peter Stone , Scott Niekum

Effective solving of constraint problems often requires choosing good or specific search heuristics. However, choosing or designing a good search heuristic is non-trivial and is often a manual process. In this paper, rather than manually…

Artificial Intelligence · Computer Science 2018-05-11 Wei Xia , Roland H. C. Yap

In security-sensitive applications, the success of machine learning depends on a thorough vetting of their resistance to adversarial data. In one pertinent, well-motivated attack scenario, an adversary may attempt to evade a deployed system…

Cryptography and Security · Computer Science 2017-08-22 Battista Biggio , Igino Corona , Davide Maiorca , Blaine Nelson , Nedim Srndic , Pavel Laskov , Giorgio Giacinto , Fabio Roli

Contextual bandit and reinforcement learning algorithms have been successfully used in various interactive learning systems such as online advertising, recommender systems, and dynamic pricing. However, they have yet to be widely adopted in…

Machine Learning · Computer Science 2022-09-23 Sorawit Saengkyongam , Nikolaj Thams , Jonas Peters , Niklas Pfister

We study policy evaluation of offline contextual bandits subject to unobserved confounders. Sensitivity analysis methods are commonly used to estimate the policy value under the worst-case confounding over a given uncertainty set. However,…

Machine Learning · Statistics 2026-01-13 Kei Ishikawa , Niao He , Takafumi Kanamori

An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well as a given baseline strategy. In this paper, we develop and…

Machine Learning · Statistics 2016-07-14 Marek Petrik , Yinlam Chow , Mohammad Ghavamzadeh

We propose an efficient Context-Aware clustering of Bandits (CAB) algorithm, which can capture collaborative effects. CAB can be easily deployed in a real-world recommendation system, where multi-armed bandits have been shown to perform…

Machine Learning · Computer Science 2017-02-28 Shuai Li , Purushottam Kar

We study the problem of off-policy evaluation from batched contextual bandit data with multidimensional actions, often termed slates. The problem is common to recommender systems and user-interface optimization, and it is particularly…

Machine Learning · Computer Science 2021-11-04 Nikos Vlassis , Ashok Chandrashekar , Fernando Amat Gil , Nathan Kallus

Bandit algorithms have recently emerged as a powerful tool for evaluating machine learning models, including generative image models and large language models, by efficiently identifying top-performing candidates without exhaustive…

Machine Learning · Computer Science 2026-02-03 Seyed Mohammad Hadi Hosseini , Amir Najafi , Mahdieh Soleymani Baghshah