English
Related papers

Related papers: Optimal Policy Adaptation under Covariate Shift

200 papers

It is often very challenging to manually design reward functions for complex, real-world tasks. To solve this, one can instead use reward learning to infer a reward function from data. However, there are often multiple reward functions that…

Machine Learning · Computer Science 2023-06-08 Joar Skalse , Matthew Farrugia-Roberts , Stuart Russell , Alessandro Abate , Adam Gleave

Transferring reinforcement learning policies trained in physics simulation to the real hardware remains a challenge, known as the "sim-to-real" gap. Domain randomization is a simple yet effective technique to address dynamics discrepancies…

Robotics · Computer Science 2021-04-05 Ioannis Exarchos , Yifeng Jiang , Wenhao Yu , C. Karen Liu

Transfer learning refers to the promising idea of initializing model fits based on pre-training on other data. We particularly consider regression modeling settings where parameter estimates from previous data can be used as anchoring…

Methodology · Statistics 2020-07-07 Wessel N. van Wieringen , Harald Binder

This paper deals with optimal policy learning (OPL) with observational data, i.e. data-driven optimal decision-making, in multi-action (or multi-arm) settings, where a finite set of decision options is available. It is organized in three…

Machine Learning · Statistics 2024-04-01 Giovanni Cerulli

Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of…

Machine Learning · Statistics 2018-06-04 Jack Umenberger , Thomas B. Schön

Transfer learning involves taking information and insight from one problem domain and applying it to a new problem domain. Although widely used in practice, theory for transfer learning remains less well-developed. To address this, we prove…

Machine Learning · Statistics 2020-06-24 Jake Williams , Abel Tadesse , Tyler Sam , Huey Sun , George D. Montanez

In this paper, we propose a new solution to reward adaptation (RA) in reinforcement learning, where the agent adapts to a target reward function based on one or more existing source behaviors learned a priori under the same domain dynamics…

Machine Learning · Computer Science 2025-10-23 Kevin Vora , Yu Zhang

Learning to control an environment without hand-crafted rewards or expert data remains challenging and is at the frontier of reinforcement learning research. We present an unsupervised learning algorithm to train agents to achieve…

Machine Learning · Computer Science 2018-11-29 David Warde-Farley , Tom Van de Wiele , Tejas Kulkarni , Catalin Ionescu , Steven Hansen , Volodymyr Mnih

The off-policy learning paradigm allows for recommender systems and general ranking applications to be framed as decision-making problems, where we aim to learn decision policies that optimize an unbiased offline estimate of an online…

Machine Learning · Computer Science 2024-08-15 Shashank Gupta , Olivier Jeunen , Harrie Oosterhuis , Maarten de Rijke

The ability to adapt to changes in environmental contingencies is an important challenge in reinforcement learning. Indeed, transferring previously acquired knowledge to environments with unseen structural properties can greatly enhance the…

Machine Learning · Computer Science 2021-10-28 Ayman Boustati , Hana Chockler , Daniel C. McNamee

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

The main challenge of multiagent reinforcement learning is the difficulty of learning useful policies in the presence of other simultaneously learning agents whose changing behaviors jointly affect the environment's transition and reward…

A typical assumption in supervised machine learning is that the train (source) and test (target) datasets follow completely the same distribution. This assumption is, however, often violated in uncertain real-world applications, which…

Machine Learning · Computer Science 2021-08-17 Masahiro Nomura , Yuta Saito

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

We introduce a distributionally robust approach that enhances the reliability of offline policy evaluation in contextual bandits under general covariate shifts. Our method aims to deliver robust policy evaluation results in the presence of…

Machine Learning · Computer Science 2024-08-12 Yihong Guo , Hao Liu , Yisong Yue , Anqi Liu

We study a problem of best-effort adaptation motivated by several applications and considerations, which consists of determining an accurate predictor for a target domain, for which a moderate amount of labeled samples are available, while…

Machine Learning · Computer Science 2023-05-11 Pranjal Awasthi , Corinna Cortes , Mehryar Mohri

Policy gradient methods are among the most effective methods in challenging reinforcement learning problems with large state and/or action spaces. However, little is known about even their most basic theoretical convergence properties,…

Machine Learning · Computer Science 2020-10-16 Alekh Agarwal , Sham M. Kakade , Jason D. Lee , Gaurav Mahajan

This study proposes an end-to-end algorithm for policy learning in causal inference. We observe data consisting of covariates, treatment assignments, and outcomes, where only the outcome corresponding to the assigned treatment is observed.…

Econometrics · Economics 2025-12-30 Masahiro Kato

Offline Reinforcement learning is commonly used for sequential decision-making in domains such as healthcare and education, where the rewards are known and the transition dynamics $T$ must be estimated on the basis of batch data. A key…

Machine Learning · Computer Science 2023-08-10 Leo Benac , Sonali Parbhoo , Finale Doshi-Velez

This paper focuses on the problem of detecting and reacting to changes in the distribution of a sensorimotor controller's observables. The key idea is the design of switching policies that can take conformal quantiles as input, which we…