English
Related papers

Related papers: To bootstrap or to rollout? An optimal and adaptiv…

200 papers

We consider a new family of operators for reinforcement learning with the goal of alleviating the negative effects and becoming more robust to approximation or estimation errors. Various theoretical results are established, which include…

Machine Learning · Statistics 2019-05-29 Yingdong Lu , Mark S. Squillante , Chai Wah Wu

We study offline reinforcement learning (RL) which seeks to learn a good policy based on a fixed, pre-collected dataset. A fundamental challenge behind this task is the distributional shift due to the dataset lacking sufficient exploration,…

Machine Learning · Computer Science 2023-10-11 Wenzhuo Zhou

Boltzmann exploration is a classic strategy for sequential decision-making under uncertainty, and is one of the most standard tools in Reinforcement Learning (RL). Despite its widespread use, there is virtually no theoretical understanding…

Machine Learning · Computer Science 2017-11-08 Nicolò Cesa-Bianchi , Claudio Gentile , Gábor Lugosi , Gergely Neu

While reinforcement learning algorithms provide automated acquisition of optimal policies, practical application of such methods requires a number of design decisions, such as manually designing reward functions that not only define the…

Machine Learning · Computer Science 2022-12-29 Tim G. J. Rudner , Vitchyr H. Pong , Rowan McAllister , Yarin Gal , Sergey Levine

Designing efficient learning algorithms with complexity guarantees for Markov decision processes (MDPs) with large or continuous state and action spaces remains a fundamental challenge. We address this challenge for entropy-regularized MDPs…

Machine Learning · Computer Science 2025-06-05 Matthieu Meunier , Christoph Reisinger , Yufei Zhang

Double/debiased machine learning (DML) provides a general framework for inference with high-dimensional or otherwise complex nuisance parameters by combining Neyman-orthogonal scores with cross-fitting, thereby circumventing classical…

Statistics Theory · Mathematics 2026-04-21 Ziming Lin , Fang Han

This paper reviews the topological groundwork for the study of reinforcement learning (RL) by focusing on the structure of state, action, and policy spaces. We begin by recalling key mathematical concepts such as complete metric spaces,…

Machine Learning · Computer Science 2025-05-21 David Krame Kadurha , Domini Jocema Leko Moutouo , Yae Ulrich Gaba

For continuous systems modeled by dynamical equations such as ODEs and SDEs, Bellman's Principle of Optimality takes the form of the Hamilton-Jacobi-Bellman (HJB) equation, which provides the theoretical target of reinforcement learning…

Machine Learning · Computer Science 2025-10-28 Haruki Settai , Naoya Takeishi , Takehisa Yairi

In reinforcement learning (RL), aligning agent behavior with specific objectives typically requires careful design of the reward function, which can be challenging when the desired objectives are complex. In this work, we propose an…

Machine Learning · Computer Science 2025-09-05 Yuting Tang , Yivan Zhang , Johannes Ackermann , Yu-Jie Zhang , Soichiro Nishimori , Masashi Sugiyama

We study whether a risk-sensitive objective from asset-pricing theory -- recursive utility -- improves reinforcement learning for portfolio allocation. The Bellman equation under recursive utility involves a certainty equivalent (CE) of…

General Finance · Quantitative Finance 2026-03-25 Minkey Chang

In reinforcement learning, the objective is almost always defined as a \emph{cumulative} function over the rewards along the process. However, there are many optimal control and reinforcement learning problems in various application fields,…

Machine Learning · Computer Science 2024-04-15 Wei Cui , Wei Yu

This paper investigates estimating the variance of a temporal-difference learning agent's update target. Most reinforcement learning methods use an estimate of the value function, which captures how good it is for the agent to be in a…

Artificial Intelligence · Computer Science 2018-02-15 Craig Sherstan , Brendan Bennett , Kenny Young , Dylan R. Ashley , Adam White , Martha White , Richard S. Sutton

We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of…

Machine Learning · Computer Science 2020-03-30 Philip Amortila , Doina Precup , Prakash Panangaden , Marc G. Bellemare

The block maxima method is a standard approach for analyzing the extremal behavior of a potentially multivariate time series. It has recently been found that the classical approach based on disjoint block maxima may be universally improved…

Statistics Theory · Mathematics 2025-03-26 Axel Bücher , Torben Staud

Reward shaping has been applied widely to accelerate Reinforcement Learning (RL) agents' training. However, a principled way of designing effective reward shaping functions, especially for complex continuous control problems, remains…

Machine Learning · Computer Science 2026-02-12 Mateo Juliani , Mingxuan Li , Elias Bareinboim

The multivariate linear regression model is an important tool for investigating relationships between several response variables and several predictor variables. The primary interest is in inference about the unknown regression coefficient…

Statistics Theory · Mathematics 2017-09-13 Daniel J. Eck

We propose and analyze a model-based bootstrap for transition kernels in finite controlled Markov chains (CMCs) with possibly nonstationary or history-dependent control policies, a setting that arises naturally in offline reinforcement…

Machine Learning · Statistics 2026-05-13 Ziwei Su , Imon Banerjee , Diego Klabjan

Learning models of the environment from data is often viewed as an essential component to building intelligent reinforcement learning (RL) agents. The common practice is to separate the learning of the model from its use, by constructing a…

Machine Learning · Computer Science 2020-11-09 Christopher Grimm , André Barreto , Satinder Singh , David Silver

This paper introduces novel Bellman mappings (B-Maps) for value iteration (VI) in distributed reinforcement learning (DRL), where agents are deployed over an undirected, connected graph/network with arbitrary topology -- but without a…

Machine Learning · Computer Science 2025-10-09 Yuki Akiyama , Konstantinos Slavakis

We study multi-objective reinforcement learning with nonlinear preferences over trajectories. That is, we maximize the expected value of a nonlinear function over accumulated rewards (expected scalarized return or ESR) in a multi-objective…

Machine Learning · Computer Science 2025-02-19 Nianli Peng , Muhang Tian , Brandon Fain