paper-with-me

홈 › Papers

No-harm principle, rationality, and Pareto optimality in games

2021-01-26 · Shaun Hargreaves Heap, Mehmet S. Ismail

Mill's classic argument for liberty requires that people's exercise of freedom should be governed by a no-harm principle (NHP). In this paper, we develop the concept of a no-harm equilibrium in $n$-person games where players maximize utility subject to the constraint of the NHP. Our main result is in the spirit of the fundamental theorems of welfare economics. We show that for every initial `reference point' in a game the associated no-harm equilibrium is Pareto efficient and, conversely, every Pareto efficient point can be supported as a no-harm equilibrium for some initial reference point.

📄 PDF Abstract BibTeX arXiv:2101.10723

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

An Optimal Procedure to Check Pareto-Optimality in House Markets with Single-Peaked Preferences

2020-02-14 · Aurélie Beynier, Nicolas Maudet, Simon Rey, Parham Shams

Recently, the problem of allocating one resource per agent with initial endowments (house markets) has seen a renewed interest: indeed, while in the domain of strict preferences the Top Trading Cycle algorithm is known t…

Pareto Optimality in No-Harm Fairness

2019-09-25 · Natalia Martinez, Martin Bertran, Guillermo Sapiro

Common fairness definitions in machine learning focus on balancing various notions of disparity and utility. In this work we study fairness in the context of risk disparity among sub-populations. We introduce the framewo…

Fairness

Strategically Robust Multi-Agent Reinforcement Learning with Linear Function Approximation

2026-03-10 · Jake Gonzales, Max Horwitz, Eric Mazumdar, Lillian J. Ratliff arxiv

Provably efficient and robust equilibrium computation in general-sum Markov games remains a core challenge in multi-agent reinforcement learning. Nash equilibrium is computationally intractable in general and brittle due…

Multi-agent Reinforcement Learning

Policy Iteration for Pareto-Optimal Policies in Stochastic Stackelberg Games

2024-05-07 · Mikoto Kudo, Yohei Akimoto

In general-sum stochastic games, a stationary Stackelberg equilibrium (SSE) does not always exist, in which the leader maximizes leader's return for all the initial states when the follower takes the best response agains…

Learnable Mixed Nash Equilibria are Collectively Rational

2025-10-16 · Geelon So, Yi-An Ma arxiv

We extend the study of learning in games to dynamics that exhibit non-asymptotic stability. We do so through the notion of uniform stability, which is concerned with equilibria of individually utility-seeking dynamics. P…