7 papers
Can You Trust Your Preference Models? Stackelberg Games for Alignment
Riccardo Formenti, Aditya Agrawal, Vikas Garg
Language models are frequently aligned to human preferences via imperfect evaluators whose errors can be exploited during optimization. We train policies to search for comparisons…
Characterizing Opinion Evolution of Networked LLMs
Caleb Probine, Yigit Ege Bayiz, Filippos Fotiadis +3
Large language models (LLMs) increasingly interact with one another in multi-agent systems, from simulations of human discourse to influence operations and fully LLM-driven social…
When Should Agents Coordinate in Differentiable Sequential Decision Problems?
Caleb Probine, Su Ann Low, David Fridovich-Keil +1
Multi-robot teams must coordinate to operate effectively. When a team operates in an uncoordinated manner, and agents choose actions that are only individually optimal, the team's…
Multi-Environment POMDPs: Discrete Model Uncertainty Under Partial Observability
Eline M. Bovy, Caleb Probine, Marnix Suilen +2
Multi-environment POMDPs (ME-POMDPs) extend standard POMDPs with discrete model uncertainty. ME-POMDPs represent a finite set of POMDPs that share the same state, action, and obser…
Designing Inferable Signaling Schemes for Bayesian Persuasion
Caleb Probine, Mustafa O. Karabag, Ufuk Topcu
In Bayesian persuasion, an informed sender, who observes a state, commits to a randomized signaling scheme that guides a self-interested receiver's actions. Classical models assume…
Privacy-preserving Nash Equilibrium Synthesis with Partially Ordered Temporal Objectives
Caleb Probine, Abhishek Kulkarni, Ufuk Topcu
Nash equilibrium is a central solution concept for reasoning about self-interested agents. We address the problem of synthesizing Nash equilibria in two-player deterministic games…
A Decentralized Shotgun Approach for Team Deception
Caleb Probine, Mustafa O. Karabag, Ufuk Topcu
Deception is helpful for agents masking their intentions from an observer. We consider a team of agents deceiving their supervisor. The supervisor defines nominal behavior for the…