English
Related papers

Related papers: Sample Complexity Reduction via Policy Difference …

200 papers

A key goal in stochastic contextual linear bandits is to efficiently learn a near-optimal policy. Prior algorithms for this problem learn a policy by strategically sampling actions but naively (passively) sampling contexts from the…

Machine Learning · Computer Science 2026-05-26 Emma Brunskill , Ishani Karmarkar , Zhaoqi Li

Balancing exploration and exploitation remains a key challenge in reinforcement learning (RL). State-of-the-art RL algorithms suffer from high sample complexity, particularly in the sparse reward case, where they can do no better than to…

Machine Learning · Computer Science 2020-01-22 Philippe Morere , Gilad Francis , Tom Blau , Fabio Ramos

Excessively changing policies in many real world scenarios is difficult, unethical, or expensive. After all, doctor guidelines, tax codes, and price lists can only be reprinted so often. We may thus want to only change a policy when it is…

Machine Learning · Statistics 2019-10-16 Benjamin Lansdell , Sofia Triantafillou , Konrad Kording

Improving sample efficiency is central to Reinforcement Learning (RL), especially in environments where the rewards are sparse. Some recent approaches have proposed to specify reward functions as manually designed or learned reward…

Machine Learning · Computer Science 2024-01-26 Shuai Han , Mehdi Dastani , Shihan Wang

In this paper, we consider a best action identification problem in the stochastic linear bandit setup with a fixed confident constraint. In the considered best action identification problem, instead of minimizing the accumulative regret as…

Machine Learning · Computer Science 2018-12-04 Jun Geng , Lifeng Lai

In contextual linear bandits, the reward function is assumed to be a linear combination of an unknown reward vector and a given embedding of context-arm pairs. In practice, the embedding is often learned at the same time as the reward…

Machine Learning · Computer Science 2022-12-20 Andrea Tirinzoni , Matteo Pirotta , Alessandro Lazaric

We introduce the problem of model selection for contextual bandits, where a learner must adapt to the complexity of the optimal policy while balancing exploration and exploitation. Our main result is a new model selection guarantee for…

Machine Learning · Computer Science 2019-11-15 Dylan J. Foster , Akshay Krishnamurthy , Haipeng Luo

Pure exploration in episodic Reinforcement Learning has primarily focused on Best Policy Identification (BPI), which seeks to identify a (near)-optimal policy with high confidence. Motivated by practical settings where a ``good enough''…

Machine Learning · Computer Science 2026-05-25 Zitian Li , Wang Chi Cheung

Many reinforcement learning algorithms, particularly those that rely on return estimates for policy improvement, can suffer from poor sample efficiency and training instability due to high-variance return estimates. In this paper we…

Machine Learning · Computer Science 2026-01-06 Alexander W. Goodall , Edwin Hamel-De le Court , Francesco Belardinelli

Reward-biased maximum likelihood estimation (RBMLE) is a classic principle in the adaptive control literature for tackling explore-exploit trade-offs. This paper studies the stochastic contextual bandit problem with general bounded reward…

Machine Learning · Computer Science 2022-05-31 Yu-Heng Hung , Ping-Chun Hsieh

Learning to plan for long horizons is a central challenge in episodic reinforcement learning problems. A fundamental question is to understand how the difficulty of the problem scales as the horizon increases. Here the natural measure of…

Machine Learning · Computer Science 2020-07-10 Ruosong Wang , Simon S. Du , Lin F. Yang , Sham M. Kakade

We study the contextual multi-armed bandit problem with a finite context space (a.k.a. subpopulations), where the learner recommends a best action for each context and is evaluated by context-weighted simple regret. Our guarantees are…

Machine Learning · Computer Science 2026-05-20 Mohammad Shahverdikondori , Jalal Etesami , Negar Kiyavash

We consider the problem of contextual bandits and imitation learning, where the learner lacks direct knowledge of the executed action's reward. Instead, the learner can actively query an expert at each round to compare two actions and…

Machine Learning · Computer Science 2023-07-25 Ayush Sekhari , Karthik Sridharan , Wen Sun , Runzhe Wu

Why do reinforcement learning (RL) policies fail or succeed? This is a challenging question due to the complex, high-dimensional nature of agent-environment interactions. In this work, we take a causal perspective on explaining the behavior…

Machine Learning · Statistics 2025-07-22 Armin Kekić , Jan Schneider , Dieter Büchler , Bernhard Schölkopf , Michel Besserve

We study offline reinforcement learning in average-reward MDPs, which presents increased challenges from the perspectives of distribution shift and non-uniform coverage, and has been relatively underexamined from a theoretical perspective.…

Machine Learning · Computer Science 2026-04-23 Matthew Zurek , Guy Zamir , Yudong Chen

While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors…

Machine Learning · Computer Science 2023-06-27 Raj Ghugare , Homanga Bharadhwaj , Benjamin Eysenbach , Sergey Levine , Ruslan Salakhutdinov

Reward-free reinforcement learning (RF-RL), a recently introduced RL paradigm, relies on random action-taking to explore the unknown environment without any reward feedback information. While the primary goal of the exploration phase in…

Machine Learning · Computer Science 2023-03-23 Ruiquan Huang , Jing Yang , Yingbin Liang

Meta reinforcement learning (RL) allows agents to leverage experience across a distribution of tasks on which the agent can train at will, enabling faster learning of optimal policies on new test tasks. Despite its success in improving…

Machine Learning · Computer Science 2026-05-27 Tingting Ni , Maryam Kamgarpour

In reward-free reinforcement learning (RL), an agent explores the environment first without any reward information, in order to achieve certain learning goals afterwards for any given reward. In this paper we focus on reward-free RL under…

Machine Learning · Computer Science 2023-03-21 Yuan Cheng , Ruiquan Huang , Jing Yang , Yingbin Liang

Reinforcement learning (RL) algorithms aim to learn optimal decisions in unknown environments through experience of taking actions and observing the rewards gained. In some cases, the environment is not influenced by the actions of the RL…