Free-Energy Equilibria: Toward a Theory of Interactions Between Boundedly-Rational Agents | OpenReview
We propose a novel framework for modelling strategic interactions between boundedly-rational agents in complex, partially observable environments. Our approach introduces agents that minimize a free-energy functional, capturing the divergence between their beliefs about future trajectories and their preferences, which are represented by a biased probabilistic model. We extend this to multi-agent settings and introduce Free-Energy Equilibria, a new class of game-theoretic solution concepts. We begin by establishing the relationship between Free-Energy Equilibria and existing game-theoretic solution concepts. Then, we propose an approach to studying cooperation by contrasting Free-Energy Equilibria with joint free-energy minimization, extending key concepts from mechanism design. Our framework allows for modelling interactions between agents with varying levels of rationality and biased or incorrect world models, providing insights into human-AI interaction and AI alignment. Enter your f
Verifying your browser | OpenReview Verifying your browser Complete the check below to continue to OpenReview Please complete the verification above. Have an OpenReview account? Sign in to skip this check.
related reading
- Towards a scale-free theory of intelligent agencymindthefuture.info
- Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
- [2608.03958] A game theory for foundation models shows new paths to rational cooperation through similarity inferencearxiv.org
- [2304.03442] Generative Agents: Interactive Simulacra of Human Behaviorarxiv.org
- Embedded Agency (full-text version) — LessWronglesswrong.com
- [1902.09469] Embedded Agencyarxiv.org
- pdfopenreview.net
- Active Inference and Intentional Behaviourarxiv.org
- Free energy principle - Wikipediaen.wikipedia.org
- Game theory - Wikipediaen.wikipedia.org
- Agent vs Agent · Ishaan Singhishaans22.com
- Beliefs are Chosen to Serve Goals — LessWronglesswrong.com