English
Related papers

Related papers: When is Realizability Sufficient for Off-Policy Re…

200 papers

We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of…

The paper deals with a risk averse dynamic programming problem with infinite horizon. First, the required assumptions are formulated to have the problem well defined. Then the Bellman equation is derived, which may be also seen as a…

Optimization and Control · Mathematics 2022-08-04 Martin Šmíd , Miloš Kopa

Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its…

Machine Learning · Computer Science 2020-08-12 Omer Gottesman , Joseph Futoma , Yao Liu , Sonali Parbhoo , Leo Anthony Celi , Emma Brunskill , Finale Doshi-Velez

Coverage conditions -- which assert that the data logging distribution adequately covers the state space -- play a fundamental role in determining the sample complexity of offline reinforcement learning. While such conditions might seem…

Machine Learning · Computer Science 2022-10-11 Tengyang Xie , Dylan J. Foster , Yu Bai , Nan Jiang , Sham M. Kakade

Effectively leveraging large, previously collected datasets in reinforcement learning (RL) is a key challenge for large-scale real-world applications. Offline RL algorithms promise to learn effective policies from previously-collected,…

Machine Learning · Computer Science 2020-08-20 Aviral Kumar , Aurick Zhou , George Tucker , Sergey Levine

Improving data utilization efficiency is critical for scaling reinforcement learning (RL) for long-horizon tasks where generating trajectories is expensive. However, the dominant RL methods for LLMs are largely on-policy: they update each…

In this paper we present a new way of predicting the performance of a reinforcement learning policy given historical data that may have been generated by a different policy. The ability to evaluate a policy from historical data is important…

Machine Learning · Computer Science 2016-04-05 Philip S. Thomas , Emma Brunskill

Off-policy evaluation often refers to two related tasks: estimating the expected return of a policy and estimating its value function (or other functions of interest, such as density ratios). While recent works on marginalized importance…

Machine Learning · Computer Science 2022-10-28 Audrey Huang , Nan Jiang

Model-free reinforcement learning algorithms can compute policy gradients given sampled environment transitions, but require large amounts of data. In contrast, model-based methods can use the learned model to generate new data, but model…

Machine Learning · Computer Science 2022-03-04 Lukas P. Fröhlich , Maksym Lefarov , Melanie N. Zeilinger , Felix Berkenkamp

Reinforcement Learning aims at identifying and evaluating efficient control policies from data. In many real-world applications, the learner is not allowed to experiment and cannot gather data in an online manner (this is the case when…

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

Adversarial Imitation Learning (AIL) faces challenges with sample inefficiency because of its reliance on sufficient on-policy data to evaluate the performance of the current policy during reward function updates. In this work, we study the…

Machine Learning · Computer Science 2024-05-28 Yilei Chen , Vittorio Giammarino , James Queeney , Ioannis Ch. Paschalidis

Reinforcement learning algorithms describe how an agent can learn an optimal action policy in a sequential decision process, through repeated experience. In a given environment, the agent policy provides him some running and terminal…

Theoretical Economics · Economics 2020-03-24 Arthur Charpentier , Romuald Elie , Carl Remlinger

Reinforcement Learning (RL) has demonstrated tremendous empirical success across numerous challenging domains. However, we lack a strong theoretical understanding of the statistical complexity of RL in environments with large state spaces,…

Machine Learning · Computer Science 2025-06-03 Gene Li

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

This paper considers the problem of solving constrained reinforcement learning (RL) problems with anytime guarantees, meaning that the algorithmic solution must yield a constraint-satisfying policy at every iteration of its evolution. Our…

Systems and Control · Electrical Eng. & Systems 2025-10-03 Pol Mestres , Arnau Marzabal , Jorge Cortés

Function approximation has been an indispensable component in modern reinforcement learning algorithms designed to tackle problems with large state spaces in high dimensions. This paper reviews recent results on error analysis for these…

Machine Learning · Computer Science 2024-02-27 Jihao Long , Jiequn Han

Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training…

Machine Learning · Statistics 2022-10-11 Shentao Yang , Zhendong Wang , Huangjie Zheng , Yihao Feng , Mingyuan Zhou

Off-policy reinforcement learning has many applications including: learning from demonstration, learning multiple goal seeking policies in parallel, and representing predictive knowledge. Recently there has been an proliferation of new…

Machine Learning · Computer Science 2016-04-01 Adam White , Martha White

Off-policy reinforcement learning aims to leverage experience collected from prior policies for sample-efficient learning. However, in practice, commonly used off-policy approximate dynamic programming methods based on Q-learning and…

Machine Learning · Computer Science 2019-11-26 Aviral Kumar , Justin Fu , George Tucker , Sergey Levine

Most of the existing works for reinforcement learning (RL) with general function approximation (FA) focus on understanding the statistical complexity or regret bounds. However, the computation complexity of such approaches is far from being…

Machine Learning · Computer Science 2023-04-19 Dingwen Kong , Ruslan Salakhutdinov , Ruosong Wang , Lin F. Yang