Search Results for author: Johannes Treutlein

Found 7 papers, 3 papers with code

COLA: Consistent Learning with Opponent-Learning Awareness

1 code implementation8 Mar 2022 Timon Willi, Alistair Letcher, Johannes Treutlein, Jakob Foerster

Finally, in an empirical evaluation on a set of general-sum games, we find that COLA finds prosocial solutions and that it converges under a wider range of learning rates than HOLA and LOLA.

CoLA

A New Formalism, Method and Open Issues for Zero-Shot Coordination

1 code implementation11 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.

Multi-agent Reinforcement Learning

Incentivizing honest performative predictions with proper scoring rules

1 code implementation28 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.

Normative Disagreement as a Challenge for Cooperative AI

no code implementations27 Nov 2021 Julian Stastny, Maxime Riché, Alexander Lyzhov, Johannes Treutlein, Allan Dafoe, Jesse Clifton

However, the mixed-motive environments typically studied have a single cooperative outcome on which all agents can agree.

Path Independent Equilibrium Models Can Better Exploit Test-Time Computation

no code implementations18 Nov 2022 Cem Anil, Ashwini Pokle, Kaiqu Liang, Johannes Treutlein, Yuhuai Wu, Shaojie Bai, Zico Kolter, Roger Grosse

Designing networks capable of attaining better performance with an increased inference budget is important to facilitate generalization to harder problem instances.

Conditioning Predictive Models: Risks and Strategies

no code implementations2 Feb 2023 Evan Hubinger, Adam Jermyn, Johannes Treutlein, Rubi Hudson, Kate Woolverton

Our intention is to provide a definitive reference on what it would take to safely make use of generative/predictive models in the absence of a solution to the Eliciting Latent Knowledge problem.

Modeling evidential cooperation in large worlds

no code implementations10 Jul 2023 Johannes Treutlein

I discuss gains from trade given uncertain beliefs about other agents and analyze how these gains decrease in several toy examples as the belief in another agent decreases.

Cannot find the paper you are looking for? You can Submit a new open access paper.