English
Related papers

Related papers: Minimax-Regret Climate Policy with Deep Uncertaint…

200 papers

We apply classical statistical decision theory to a large class of treatment choice problems with partial identification. We show that, in a general class of problems with Gaussian likelihood, all decision rules are admissible; it is…

Econometrics · Economics 2025-06-24 José Luis Montiel Olea , Chen Qiu , Jörg Stoye

Climate policy modelling is a key tool for assessing mitigation strategies in complex systems, where uncertainty is inherent and unavoidable. We present a general methodology for extensive uncertainty analysis in this field. While other…

Applications · Statistics 2026-05-15 Ian J. Burton , Femke J. M. M. Nijsse , James M. Salter

Model-based reinforcement learning (MBRL) agents typically learn world models by minimizing predictive loss. However, powerful RL optimizers inevitably exploit minor model inaccuracies, leading to simulator exploitation and a reality gap…

Machine Learning · Computer Science 2026-05-29 Christoph Dann , Yishay Mansour , Mehryar Mohri

We consider reinforcement learning (RL) in episodic MDPs with adversarial full-information reward feedback and unknown fixed transition kernels. We propose two model-free policy optimization algorithms, POWER and POWER++, and establish…

Machine Learning · Computer Science 2020-07-02 Yingjie Fei , Zhuoran Yang , Zhaoran Wang , Qiaomin Xie

LLM routing aims to select the most appropriate model for each query, balancing competing performance metrics such as accuracy and cost across a pool of language models. Prior approaches typically adopt a decoupled strategy, where the…

Artificial Intelligence · Computer Science 2026-01-05 Asterios Tsiourvas , Wei Sun , Georgia Perakis

We present an optimisation-based method for synthesising a dynamic regret optimal controller for linear systems with potentially adversarial disturbances and known or adversarial initial conditions. The dynamic regret is defined as the…

Systems and Control · Electrical Eng. & Systems 2022-05-31 Alexandre Didier , Jerome Sieber , Melanie N. Zeilinger

We study the problem of planning under model uncertainty in an online meta-reinforcement learning (RL) setting where an agent is presented with a sequence of related tasks with limited interactions per task. The agent can use its experience…

Artificial Intelligence · Computer Science 2023-01-02 Khimya Khetarpal , Claire Vernade , Brendan O'Donoghue , Satinder Singh , Tom Zahavy

We analyse the conservatism and regret of distributionally robust (DR) stochastic model predictive control (SMPC) when using moment-based ambiguity sets for modeling unknown uncertainties. To quantify the conservatism, we compare the…

Systems and Control · Electrical Eng. & Systems 2024-03-15 Maik Pfefferkorn , Venkatraman Renganathan , Rolf Findeisen

Energy systems modellers often resort to simplified system representations and deterministic model formulations (i.e., not considering uncertainty) to preserve computational tractability. However, reduced levels of detail and neglected…

Physics and Society · Physics 2022-08-18 Maria Yliruka , Stefano Moret , Nilay Shah

Until recently, analysis of optimal global climate policy has focused on mitigation. Exploration of policies to meet the 1.5{\deg}C target have brought carbon dioxide removal (CDR), a second instrument, into the climate policy mainstream.…

General Economics · Economics 2019-03-07 Mariia Belaia

This paper presents a chance constrained information gap decision model for multi-period microgrid expansion planning (MMEP) considering two categories of uncertainties, namely random and non-random uncertainties. The main task of MMEP is…

Optimization and Control · Mathematics 2017-08-25 Xiaoyu Cao , Jianxue Wang , Bo Zeng

In this paper, we propose a learning approach to analyze dynamic systems with asymmetric information structure. Instead of adopting a game theoretic setting, we investigate an online quadratic optimization problem driven by system noises…

Optimization and Control · Mathematics 2018-11-05 Cheng Tan , Wing Shing Wong

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli

We study non-rectangular robust Markov decision processes under the average-reward criterion, where the ambiguity set couples transition probabilities across states and the adversary commits to a stationary kernel for the entire horizon. We…

Optimization and Control · Mathematics 2026-03-11 Shengbo Wang , Nian Si

Practitioners often use data from a randomized controlled trial to learn a treatment assignment policy that can be deployed on a target population. A recurring concern in doing so is that, even if the randomized trial was well-executed…

Econometrics · Economics 2023-04-25 Lihua Lei , Roshni Sahoo , Stefan Wager

Prediction sets can wrap around any ML model to cover unknown test outcomes with a guaranteed probability. Yet, it remains unclear how to use them optimally for downstream decision-making. Here, we propose a decision-theoretic framework…

Machine Learning · Statistics 2026-02-10 Tao Wang , Edgar Dobriban

We present an algorithm guaranteeing dynamic regret bounds for online omniprediction with long term constraints. The goal in this recently introduced problem is for a learner to generate a sequence of predictions which are broadcast to a…

Machine Learning · Computer Science 2025-10-09 Yahav Bechavod , Jiuyao Lu , Aaron Roth

Integrating the gas and district heating with the electrical grid in a multi-energy grid has been shown to provide flexibility and prevent bottlenecks in the operation of electrical distribution grids. This integration assumes a top-down…

Systems and Control · Electrical Eng. & Systems 2024-11-28 Marwan Mostafa , Davood Babazadeh , Christian Becker

We consider the infinite-horizon LQR control problem. Motivated by competitive analysis in online learning, as a criterion for controller design we introduce the dynamic regret, defined as the difference between the LQR cost of a causal…

Optimization and Control · Mathematics 2023-04-14 Oron Sabag , Gautam Goel , Sahin Lale , Babak Hassibi

In this work, we consider the regret minimization problem for reinforcement learning in latent Markov Decision Processes (LMDP). In an LMDP, an MDP is randomly drawn from a set of $M$ possible MDPs at the beginning of the interaction, but…

Machine Learning · Computer Science 2021-02-10 Jeongyeol Kwon , Yonathan Efroni , Constantine Caramanis , Shie Mannor