Overview
We develop the concept of shared protentions—shared anticipatory states—in multi-agent Active Inference. Protentions are future-directed expectations that shape perception and action; here we formalize how agents can develop shared protentions through coupled generative models, enabling coordinated anticipatory behavior in multi-agent systems.
shared protentionsmulti-agentActive Inferenceanticipationcoupled generative modelscoordinationpredictive processing
Overview source: Curated paper metadata.
Methods and contributions
Read the source for the full argument, qualifications, and evidence.
Findings and contributions
- Replacing the trivial interface with a hom over all agents' blankets yields agents that predict their own and companions' actions plus the environment's response, a starting point for formal theory of mind.
- The authors argue that if agents' models can be glued into a sheaf of world models, the agents inhabit a shared universe and may be said to share protentions; failure to glue indicates disagreement.
- The paper proposes shared protentions as an emergent, possibly necessary, property of collective self-organization.
- The authors state the proposal is broad and does not yet provide a specific testable model, leaving that to future work.
Methods
- Husserlian time-consciousness as conceptual basis for shared goals — Uses Husserl's retention, primal impression, and protention, extended to intersubjectivity, to cast shared goals as shared protentions.
- Polynomial-functor formalization of agent boundaries and generative models — Represents agents' Markov blankets as polynomial functors with stochastic feedback, using tensors and hom polynomials to model multi-agent prediction.
- Sheaf- and topos-theoretic gluing of agents' world models — Proposes gluing agents' spatial generative models into a sheaf of world models and their toposes into a consensus topos representing shared understanding.
Summary sources: Paper metadata and evidence · Extracted source text.
PDF downloads
Archived files available directly from this site.
- 2024_SharedProtentions.pdf PDF · 0.31 MiB · extracted-text source
Citation
Citation metadata follows the unified bibliography.
Albarracin, Mahault; Pitliya, Riddhi J.; St. Clere Smithe, Toby; Friedman, Daniel Ari; Friston, Karl; Ramstead, Maxwell J. D.. 2024. Shared Protentions in Multi-Agent Active Inference. Entropy. DOI: 10.3390/e26040303. URL: https://doi.org/10.3390/e26040303.
Catalog details and resources
Related in Active Inference
Other catalogued works in the same domain.