English
Related papers

Related papers: Geometry Meets Incentives: Sample-Efficient Incent…

200 papers

This survey (re)introduces reinforcement learning methods to economists. The curse of dimensionality limits how far exact dynamic programming can be effectively applied, forcing us to rely on suitably "small" problems or our ability to…

General Economics · Economics 2026-03-25 Pranjal Rawat

Preference-based feedback is important for many applications in machine learning where evaluation of a reward function is not feasible. Notable recent examples arise in preference alignment for large language models, including in…

Balancing exploration and exploitation is a fundamental part of reinforcement learning, yet most state-of-the-art algorithms use a naive exploration protocol like $\epsilon$-greedy. This contributes to the problem of high sample complexity,…

Machine Learning · Computer Science 2019-11-21 Tom Blau , Lionel Ott , Fabio Ramos

This paper considers the use of a simple posterior sampling algorithm to balance between exploration and exploitation when learning to optimize actions such as in multi-armed bandit problems. The algorithm, also known as Thompson Sampling,…

Machine Learning · Computer Science 2014-02-04 Daniel Russo , Benjamin Van Roy

Current practice in parameter space exploration in euclidean space is dominated by randomized sampling or design of experiment methods. The biggest issue with these methods is not keeping track of what part of parameter space has been…

Machine Learning · Computer Science 2023-03-16 Avinash Kumar , Anish Kumar , Sumit Sharma , Surjeet Singh , Kumar Vardhan

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be…

Machine Learning · Computer Science 2024-07-02 Alessio Russo , Alexandre Proutiere

Biological agents have meaningful interactions with their environment despite the absence of immediate reward signals. In such instances, the agent can learn preferred modes of behaviour that lead to predictable states -- necessary for…

Artificial Intelligence · Computer Science 2021-07-20 Noor Sajid , Panagiotis Tigas , Alexey Zakharov , Zafeirios Fountas , Karl Friston

Exploration algorithms for reinforcement learning typically replace or augment the reward function with an additional ``intrinsic'' reward that trains the agent to seek previously unseen states of the environment. Here, we consider an…

Machine Learning · Computer Science 2025-09-30 Kevin McKee , Eric Alt , Andrew Grebenisan , Mick van Gelderen , Gary Miguel

We provide an approach for the analysis of randomised exploration algorithms like Thompson sampling that does not rely on forced optimism or posterior inflation. With this, we demonstrate that in the $d$-dimensional linear bandit setting,…

Machine Learning · Computer Science 2025-02-14 Marc Abeille , David Janz , Ciara Pike-Burke

The literature on bandit learning and regret analysis has focused on contexts where the goal is to converge on an optimal action in a manner that limits exploration costs. One shortcoming imposed by this orientation is that it does not…

Machine Learning · Computer Science 2017-05-01 Daniel Russo , David Tse , Benjamin Van Roy

We study here the problem of learning the exploration exploitation trade-off in the contextual bandit problem with linear reward function setting. In the traditional algorithms that solve the contextual bandit problem, the exploration is a…

Machine Learning · Computer Science 2020-05-06 Djallel Bouneffouf , Emmanuelle Claeys

Exploration is a prerequisite for learning useful behaviors in sparse-reward, long-horizon tasks, particularly within 3D environments. Curiosity-driven reinforcement learning addresses this via intrinsic rewards derived from the mismatch…

Machine Learning · Computer Science 2026-05-22 Lily Goli , Justin Kerr , Daniele Reda , Alec Jacobson , Andrea Tagliasacchi , Angjoo Kanazawa

We study contextual bandits in the presence of a stage-wise constraint when the constraint must be satisfied both with high probability and in expectation. We start with the linear case where both the reward function and the stage-wise…

Machine Learning · Computer Science 2025-08-22 Aldo Pacchiano , Mohammad Ghavamzadeh , Peter Bartlett

In this paper, we study the multi-objective bandits (MOB) problem, where a learner repeatedly selects one arm to play and then receives a reward vector consisting of multiple objectives. MOB has found many real-world applications as varied…

Machine Learning · Computer Science 2019-05-31 Shiyin Lu , Guanghui Wang , Yao Hu , Lijun Zhang

Reinforcement learning provides an automated framework for learning behaviors from high-level reward specifications, but in practice the choice of reward function can be crucial for good results -- while in principle the reward only needs…

Machine Learning · Computer Science 2022-10-19 Abhishek Gupta , Aldo Pacchiano , Yuexiang Zhai , Sham M. Kakade , Sergey Levine

Exploration in reinforcement learning (RL) remains an open challenge. RL algorithms rely on observing rewards to train the agent, and if informative rewards are sparse the agent learns slowly or may not learn at all. To improve exploration…

Machine Learning · Computer Science 2024-11-12 Simone Parisi , Alireza Kazemipour , Michael Bowling

We study reward-free reinforcement learning (RL) with linear function approximation, where the agent works in two phases: (1) in the exploration phase, the agent interacts with the environment but cannot access the reward; and (2) in the…

Machine Learning · Computer Science 2024-02-15 Junkai Zhang , Weitong Zhang , Quanquan Gu

The contextual bandit literature has traditionally focused on algorithms that address the exploration-exploitation tradeoff. In particular, greedy algorithms that exploit current estimates without any exploration may be sub-optimal in…

Machine Learning · Statistics 2020-04-21 Hamsa Bastani , Mohsen Bayati , Khashayar Khosravi

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

Contextual dueling bandit is used to model the bandit problems, where a learner's goal is to find the best arm for a given context using observed noisy human preference feedback over the selected arms for the past contexts. However,…

Machine Learning · Computer Science 2025-04-17 Arun Verma , Zhongxiang Dai , Xiaoqiang Lin , Patrick Jaillet , Bryan Kian Hsiang Low