English
Related papers

Related papers: Conformal Policy Control

200 papers

An important problem in sequential decision-making under uncertainty is to use limited data to compute a safe policy, i.e., a policy that is guaranteed to perform at least as well as a given baseline strategy. In this paper, we develop and…

Machine Learning · Statistics 2016-07-14 Marek Petrik , Yinlam Chow , Mohammad Ghavamzadeh

Safe exploration presents a major challenge in reinforcement learning (RL): when active data collection requires deploying partially trained policies, we must ensure that these policies avoid catastrophically unsafe regions, while still…

Machine Learning · Computer Science 2021-04-27 Homanga Bharadhwaj , Aviral Kumar , Nicholas Rhinehart , Sergey Levine , Florian Shkurti , Animesh Garg

Using offline datasets to evaluate conversational agents often fails to cover rare scenarios or to support testing new policies. This has motivated the use of controllable user simulators for targeted, counterfactual evaluation, typically…

Artificial Intelligence · Computer Science 2026-05-13 Guy Tennenholtz , Ofer Meshi , Amir Globerson , Uri Shalit , Jihwan Jeong , Craig Boutilier

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…

Overconservatism has long been recognized as a major issue with robust optimization, despite its key advantages of tractability, performance guarantee, and limited information. To address this issue, a new criterion is proposed that can…

Optimization and Control · Mathematics 2026-03-20 Yingjie Lan

We consider the problem of reinforcement learning when provided with (1) a baseline control policy and (2) a set of constraints that the learner must satisfy. The baseline policy can arise from demonstration data or a teacher agent and may…

Machine Learning · Computer Science 2021-07-13 Tsung-Yen Yang , Justinian Rosca , Karthik Narasimhan , Peter J. Ramadge

When a machine learning model is deployed, its predictions can alter its environment, as better informed agents strategize to suit their own interests. With such alterations in mind, existing approaches to uncertainty quantification break.…

Machine Learning · Statistics 2024-11-05 Daniel Csillag , Claudio José Struchiner , Guilherme Tegoni Goedert

Modeling the purposeful behavior of imperfect agents from a small number of observations is a challenging task. When restricted to the single-agent decision-theoretic setting, inverse optimal control techniques assume that observed behavior…

Computer Science and Game Theory · Computer Science 2013-08-19 Kevin Waugh , Brian D. Ziebart , J. Andrew Bagnell

Safety is one of the main challenges in applying reinforcement learning to realistic environmental tasks. To ensure safety during and after training process, existing methods tend to adopt overly conservative policy to avoid unsafe…

Machine Learning · Computer Science 2023-06-27 Xiao Zhang , Hai Zhang , Hongtu Zhou , Chang Huang , Di Zhang , Chen Ye , Junqiao Zhao

As artificial agents become increasingly capable, what internal structure is *necessary* for an agent to act competently under uncertainty? Classical results show that optimal control can be *implemented* using belief states or world…

Machine Learning · Computer Science 2026-04-03 Aran Nayebi

The safe operation of an autonomous system is a complex endeavor, one pivotal element being its decision-making. Decision-making logic can formally be analyzed using model checking or other formal verification approaches. Yet, the…

Multiagent Systems · Computer Science 2023-10-05 Jan Vermaelen , Tom Holvoet

We consider adaptive decision-making problems where an agent optimizes a cumulative performance objective by repeatedly choosing among a finite set of options. Compared to the classical prediction-with-expert-advice set-up, we consider…

Machine Learning · Computer Science 2023-04-10 Michael Muehlebach

We develop a new approach to multi-label conformal prediction in which we aim to output a precise set of promising prediction candidates with a bounded number of incorrect answers. Standard conformal prediction provides the ability to adapt…

Machine Learning · Computer Science 2022-02-16 Adam Fisch , Tal Schuster , Tommi Jaakkola , Regina Barzilay

Autonomous space vehicles need adaptive control strategies that can accommodate unanticipated environmental conditions. The evaluation of new strategies can often be done only by actually trying them out in the real physical environment.…

Optimization and Control · Mathematics 2007-05-23 G. W. Greenwood , X. Song

Modern data is messy and high-dimensional, and it is often not clear a priori what are the right questions to ask. Instead, the analyst typically needs to use the data to search for interesting analyses to perform and hypotheses to test.…

Machine Learning · Statistics 2019-10-09 Daniel Russo , James Zou

The interest in using reinforcement learning (RL) controllers in safety-critical applications such as robot navigation around pedestrians motivates the development of additional safety mechanisms. Running RL-enabled systems among uncertain…

Robotics · Computer Science 2023-12-08 Kegan J. Strawn , Nora Ayanian , Lars Lindemann

In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly…

Machine Learning · Computer Science 2018-07-11 Aniruddh Raghu , Omer Gottesman , Yao Liu , Matthieu Komorowski , Aldo Faisal , Finale Doshi-Velez , Emma Brunskill

We study the problem of choosing optimal policy rules in uncertain environments using models that may be incomplete and/or partially identified. We consider a policymaker who wishes to choose a policy to maximize a particular counterfactual…

Econometrics · Economics 2020-12-22 Thomas M. Russell

Calibration has emerged as a foundational goal in ``trustworthy machine learning'', in part because of its strong decision theoretic semantics. Independent of the underlying distribution, and independent of the decision maker's utility…

Machine Learning · Statistics 2025-10-28 Shayan Kiyani , Hamed Hassani , George Pappas , Aaron Roth

We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies could in principle represent such strategies, in practice…