no code implementations • 12 Feb 2024 • Vojtech Kovarik, Caspar Oesterheld, Vincent Conitzer
In this paper, we study an interaction between AI agents where the agents run a recursive joint simulation.
no code implementations • 11 Jul 2023 • Caspar Oesterheld, Abram Demski, Vincent Conitzer
In this paper, we develop a theory of rational decision making that does not assume logical omniscience.
no code implementations • 28 May 2023 • Emanuel Tewolde, Caspar Oesterheld, Vincent Conitzer, Paul W. Goldberg
For such games, two natural equilibrium concepts have been proposed as alternative solution concepts to ex-ante optimality.
1 code implementation • 28 May 2023 • Caspar Oesterheld, Johannes Treutlein, Emery Cooper, Rubi Hudson
We show that, for binary predictions, if the influence of the expert's prediction on outcomes is bounded, it is possible to define scoring rules under which optimal reports are arbitrarily close to fixed points.
1 code implementation • 7 Jul 2022 • Scott Emmons, Caspar Oesterheld, Andrew Critch, Vincent Conitzer, Stuart Russell
In this work, we show that any locally optimal symmetric strategy profile is also a (global) Nash equilibrium.
no code implementations • NeurIPS 2021 • James Bell, Linda Linsefors, Caspar Oesterheld, Joar Skalse
This gives us a powerful tool for reasoning about the limit behaviour of agents -- for example, it lets us show that there are Newcomblike environments in which a reinforcement learning agent cannot converge to any optimal policy.
1 code implementation • 11 Jun 2021 • Johannes Treutlein, Michael Dennis, Caspar Oesterheld, Jakob Foerster
We introduce an extension of the algorithm, other-play with tie-breaking, and prove that it is optimal in the LFC problem and an equilibrium in the LFC game.
no code implementations • 21 Apr 2015 • Caspar Oesterheld
Most ethical work is done at a low level of formality.