English
Related papers

Related papers: Accelerator and Brake: Dynamic Persuasion with Dea…

200 papers

Continuous-action policies trained on a single demonstrated trajectory per scene suffer from mode collapse: samples cluster around the demonstrated maneuver and the policy cannot represent semantically distinct alternatives. Under…

Robotics · Computer Science 2026-05-15 Hengtong Lu , Victor Shea-Jay Huang , Chengmin Yang , Pengfei Jing , Jifeng Dai , Yan Xie , Benjin Zhu

We study a cooperative multi-agent bandit setting in the distributed GOSSIP model: in every round, each of $n$ agents chooses an action from a common set, observes the action's corresponding reward, and subsequently exchanges information…

Machine Learning · Computer Science 2024-10-21 John Lazarsfeld , Dan Alistarh

We consider the problem of Adverse Selection and optimal derivative design within a Principal-Agent framework. The principal's income is exposed to non-hedgeable risk factors arising, for instance, from weather or climate phenomena. She…

Computational Engineering, Finance, and Science · Computer Science 2007-10-31 U. Horst , S. Moreno

In bandit settings, optimizing long-term regret metrics requires exploration, which corresponds to sometimes taking myopically sub-optimal actions. When a long-lived principal merely recommends actions to be executed by a sequence of…

Computer Science and Game Theory · Computer Science 2026-02-25 Ramya Ramalingam , Osbert Bastani , Aaron Roth

We study the classic principal-agent model when the signal observed by the principal is chosen by the agent. We fully characterize the optimal information structure from an agent's perspective in a general moral hazard setting with limited…

Theoretical Economics · Economics 2023-07-25 Majid Mahzoon , Ali Shourideh , Ariel Zetlin-Jones

As AI agents become more autonomous, properly aligning their objectives with human preferences becomes increasingly important. We study how effectively an AI agent learns a human principal's preference in choice under risk via stated versus…

General Economics · Economics 2026-04-01 Keaton Ellis , Wanying Huang

The absence of an algorithm that effectively monitors deep learning models used in side-channel attacks increases the difficulty of evaluation. If the attack is unsuccessful, the question is if we are dealing with a resistant implementation…

Cryptography and Security · Computer Science 2021-11-30 Servio Paguada , Lejla Batina , Ileana Buhan , Igor Armendariz

In reinforcement learning, agents learn by performing actions and observing their outcomes. Sometimes, it is desirable for a human operator to \textit{interrupt} an agent in order to prevent dangerous situations from happening. Yet, as part…

Artificial Intelligence · Computer Science 2017-05-23 El Mahdi El Mhamdi , Rachid Guerraoui , Hadrien Hendrikx , Alexandre Maurer

I study endogenous learning dynamics for people who misperceive intertemporal correlations in random sequences. Biased agents face an optimal-stopping problem. They are uncertain about the underlying distribution and learn its parameters…

Economics · Quantitative Finance 2022-11-15 Kevin He

We consider a collection of linear stochastic bandit problems, each modeling the random response of different agents to proposed interventions, coupled together by a global safety constraint. We assume a central coordinator must choose…

Optimization and Control · Mathematics 2025-04-24 Arghavan Zibaie , Spencer Hutchinson , Ramtin Pedarsani , Mahnoosh Alizadeh

In the latent bandit problem, the learner has access to reward distributions and -- for the non-stationary variant -- transition models of the environment. The reward distributions are conditioned on the arm and unknown latent states. The…

Machine Learning · Computer Science 2022-07-11 Alexander Galozy , Slawomir Nowaczyk

We study active preference learning as a framework for intuitively specifying the behaviour of autonomous robots. In active preference learning, a user chooses the preferred behaviour from a set of alternatives, from which the robot learns…

Robotics · Computer Science 2020-09-30 Nils Wilde , Dana Kulic , Stephen L. Smith

This paper focuses on reinforcement learning (RL) with limited prior knowledge. In the domain of swarm robotics for instance, the expert can hardly design a reward function or demonstrate the target behavior, forbidding the use of both…

Machine Learning · Computer Science 2012-08-07 Riad Akrour , Marc Schoenauer , Michèle Sebag

Sequential decision making under uncertainty is studied in a mixed observability domain. The goal is to maximize the amount of information obtained on a partially observable stochastic process under constraints imposed by a fully observable…

Artificial Intelligence · Computer Science 2016-03-16 Mikko Lauri , Risto Ritala

Dynamic decisions are pivotal to economic policy making. We show how existing evidence from randomized control trials can be utilized to guide personalized decisions in challenging dynamic environments with budget and capacity constraints.…

Econometrics · Economics 2024-11-26 Karun Adusumilli , Friedrich Geiecke , Claudio Schilter

We study a repeated Principal Agent problem between a long lived Principal and Agent pair in a prior free setting. In our setting, the sequence of realized states of nature may be adversarially chosen, the Agent is non-myopic, and the…

Computer Science and Game Theory · Computer Science 2023-11-15 Natalie Collina , Aaron Roth , Han Shao

Preference-based reinforcement learning (PbRL) aligns a robot behavior with human preferences via a reward function learned from binary feedback over agent behaviors. We show that dynamics-aware reward functions improve the sample…

Artificial Intelligence · Computer Science 2024-02-29 Katherine Metcalf , Miguel Sarabia , Natalie Mackraz , Barry-John Theobald

We investigate a class of optimal stopping problems arising in, for example, studies considering the timing of an irreversible investment when the underlying follows a skew Brownian motion. Our results indicate that the local directional…

Probability · Mathematics 2016-08-17 Luis H. R. Alvarez E. , Paavo Salminen

A principal delegates decisions to a biased agent. Payoffs depend on a state that the principal cannot observe. Initially, the agent does not observe the state, but he can acquire information about it at a cost. We characterize the…

Theoretical Economics · Economics 2023-11-21 Ian Ball , Xin Gao

We study fair multi-agent multi-armed bandit learning under collision-only coordination. Agents cannot communicate explicitly during learning and observe only their own rewards and whether collisions occur when several agents access the…

Machine Learning · Computer Science 2026-05-05 Amir Leshem