pith. machine review for the scientific record. sign in

arxiv: 2604.27942 · v1 · submitted 2026-04-30 · 💻 cs.AI

Recognition: unknown

A Collective Variational Principle Unifying Bayesian Inference, Game Theory, and Thermodynamics

Djamel Bouchaffra , Faycal Ykhlef , Mustapha Lebbah , Hanane Azzag
Authors on Pith no claims yet

Pith reviewed 2026-05-07 06:52 UTC · model grok-4.3

classification 💻 cs.AI
keywords game-theoretic free energy principlecollective free energyNash equilibriumvariational inferenceHarsanyi dividendmulti-agent systemscollective intelligenceBayesian inference
0
0 comments X

The pith

Under bounded rationality and local information, collective free energy minimization yields approximate Nash equilibria in induced games.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper introduces the Game-Theoretic Free Energy Principle as a variational unification of Bayesian inference, game theory, and thermodynamics for multi-agent systems. It proves that agents minimizing a shared free energy under local information and bounded rationality reach stationary points that are approximate Nash equilibria of an induced stochastic game. In the converse direction, many cooperative games receive a variational representation where equilibria appear as Gibbs distributions over coalitions. The framework adds a free-energy version of the Harsanyi dividend to isolate irreducible group synergies and derives a concrete prediction of a non-monotonic link between an agent's sensory precision and its influence on the collective. Validation across neural, biological, and artificial systems supports the claim that collective intelligence can arise from the same local variational process that governs single-agent inference.

Core claim

Multi-agent systems performing local free-energy minimisation implicitly implement a stochastic game. Under bounded rationality and local information constraints, stationary points of collective free energy correspond to approximate Nash equilibria of an induced game. Conversely, a broad class of cooperative games admits a variational representation in which equilibria arise as Gibbs distributions over coalitions. The framework characterises higher-order effects through a free-energy formulation of the Harsanyi dividend, yielding a predictive theory of cooperation that includes a falsifiable non-monotonic relationship between sensory precision and agent influence, which is validated across a

What carries the argument

The collective free energy functional, whose stationary points under local constraints map to approximate Nash equilibria in the induced game and whose minimizers correspond to Gibbs distributions in the variational representation of cooperative games.

If this is right

  • Stationary points of collective free energy correspond to approximate Nash equilibria of an induced stochastic game.
  • A broad class of cooperative games admits variational representations whose equilibria are Gibbs distributions over coalitions.
  • Higher-order multi-agent synergy is isolated by a free-energy formulation of the Harsanyi dividend.
  • Sensory precision and agent influence are related non-monotonically in a way that can be tested in neural, biological, and artificial collectives.
  • Collective intelligence can emerge from local free-energy minimization without central coordination or explicit strategic reasoning.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The unification implies that observed cooperative behavior in natural systems may be explained as an implicit consequence of individual variational inference rather than explicit game solving.
  • The same variational structure could be used to engineer artificial multi-agent systems whose local updates produce stable cooperation without centralized equilibrium computation.
  • Because the framework already links to thermodynamics, it suggests that physical many-body systems viewed through collective free energy may exhibit game-like equilibrium behavior as a derived property.

Load-bearing premise

Bounded rationality together with local information constraints is sufficient for stationary points of collective free energy to be approximate Nash equilibria of the induced game.

What would settle it

An observed multi-agent system in which agents minimize collective free energy yet do not converge to approximate Nash equilibria, or a controlled experiment showing that agent influence changes monotonically with sensory precision rather than non-monotonically.

Figures

Figures reproduced from arXiv: 2604.27942 by Djamel Bouchaffra, Faycal Ykhlef, Hanane Azzag, Mustapha Lebbah.

Figure 1
Figure 1. Figure 1: Non-monotonic influence in neural ensembles. Mean Shapley value per agent as a function of sensory precision β for a population of N = 50 agents (neurons) using a Gaussian generative model (50 independent runs per precision level). Points show the mean; error bars (not visible) are smaller than the markers. The solid curve is a quadratic fit (R2 = 1.00), and the vertical dashed line indicates the optimal p… view at source ↗
Figure 2
Figure 2. Figure 2: Non-monotonic influence in fish schooling. Mean influence (Shapley value) as a function of sensory precision β for the analytic coalition model (N = 30 fish, 80 independent runs per precision level). Points show the mean; error bars represent ±1 standard deviation. The solid curve is a quadratic fit (R2 = 0.88), and the vertical dashed line indicates the optimal precision β ∗ = 2.70 where influence peaks. 6 view at source ↗
Figure 3
Figure 3. Figure 3: Non-monotonic influence in multi-agent reinforcement learning. Mean influ￾ence (Shapley value) as a function of sensory precision β for the analytic coalition model (N = 5 agents, 100 independent runs per precision level). The solid curve is a quadratic fit (R2 = 0.94), and the vertical dashed line indicates the optimal precision β ∗ = 2.59 where influence peaks. Cross-domain summary view at source ↗
Figure 4
Figure 4. Figure 4: Universal non-monotonic influence across domains. Normalised influence as a function of sensory precision β for neural ensembles (blue circles), fish schooling (green squares), and multi-agent reinforcement learning (red triangles). Each curve is normalised to its own maximum to highlight the shape. All three systems exhibit a clear inverted-U shape: influence rises to an optimal precision β ∗ (neural: 0.7… view at source ↗
Figure 5
Figure 5. Figure 5: Variational Free Energy Principle for collective intelligence. A multi-agent system induces a probability distribution over coalition structures through an energy functional encoding individual contributions and higher-order interactions via the Harsanyi decomposition of coalition synergy. Minimisation of variational free energy yields a Gibbs distribution over coalitions, which can be interpreted as Bayes… view at source ↗
read the original abstract

Collective intelligence emerges across biological, physical, and artificial systems without central coordination, yet a unifying principle governing such behaviour remains elusive. The Free Energy Principle explains how individual agents adapt through variational inference, while game theory formalises strategic interactions. Here we introduce the Game-Theoretic Free Energy Principle, a unified framework showing that multi-agent systems performing local free-energy minimisation implicitly implement a stochastic game. We prove that, under bounded rationality and local information constraints, stationary points of collective free energy correspond to approximate Nash equilibria of an induced game. Conversely, a broad class of cooperative games admits a variational representation in which equilibria arise as Gibbs distributions over coalitions, establishing a bridge between Bayesian inference and strategic interaction. To characterise higher-order effects, we introduce a free-energy formulation of the Harsanyi dividend, isolating irreducible multi-agent synergy. This yields a predictive theory of cooperation, including a falsifiable non-monotonic relationship between sensory precision and agent influence. We validate this prediction across neural, biological, and artificial multi-agent systems. These results identify a common variational principle underlying inference, thermodynamics, and game-theoretic equilibrium.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The paper introduces the Game-Theoretic Free Energy Principle, asserting that under bounded rationality and local information constraints, stationary points of collective free energy correspond to approximate Nash equilibria of an induced game. Conversely, a broad class of cooperative games admits a variational representation in which equilibria arise as Gibbs distributions over coalitions. It introduces a free-energy formulation of the Harsanyi dividend to isolate irreducible multi-agent synergy and derives a falsifiable prediction of a non-monotonic relationship between sensory precision and agent influence, which is validated across neural, biological, and artificial multi-agent systems. The framework aims to unify Bayesian inference, game theory, and thermodynamics.

Significance. If the central correspondence and quantitative predictions hold, the work would provide a novel variational bridge between individual free-energy minimization and strategic equilibria, with potential to explain emergent cooperation in decentralized systems. The Harsanyi dividend formulation and the explicit falsifiable prediction represent constructive contributions that could be tested in AI and complex systems research. However, the absence of error bounds and operational details currently limits the framework's immediate utility and testability.

major comments (2)
  1. [Proof of the Nash correspondence and stationary conditions] The derivation of the Nash correspondence (stationary conditions via variational calculus) shows that exact stationarity implies exact equilibrium only in the infinite-rationality limit. No explicit epsilon-Nash bound is derived that relates the free-energy residual or rationality parameter to payoff deviation or total-variation distance to equilibrium. This is load-bearing for the non-monotonic precision-influence prediction, as it leaves the 'approximate' regime qualitative and non-falsifiable in its current form.
  2. [Empirical validation and predictive theory of cooperation] The falsifiable prediction of a non-monotonic relationship between sensory precision and agent influence depends on the definition and selection of the precision parameter (a free parameter in the model). The empirical validation across systems provides no details on error analysis, exclusion criteria, or robustness to alternative operationalizations of precision, undermining the claim that the relationship is a genuine, parameter-independent prediction.
minor comments (2)
  1. [Abstract] The abstract is dense and interleaves multiple distinct claims; separating the forward and converse directions more clearly would improve readability.
  2. [Introduction and definitions] New terminology such as 'Game-Theoretic Free Energy Principle' and 'free-energy formulation of the Harsanyi dividend' is introduced without an explicit comparison table or section relating it to prior variational approaches in game theory (e.g., potential games or mean-field approximations).

Simulated Author's Rebuttal

2 responses · 0 unresolved

We are grateful to the referee for their detailed and constructive feedback on our manuscript. Their comments have identified key areas for improvement, particularly in making the theoretical bounds explicit and enhancing the rigor of the empirical validation. We respond to each major comment below and describe the revisions we will implement.

read point-by-point responses

  1. Referee: [Proof of the Nash correspondence and stationary conditions] The derivation of the Nash correspondence (stationary conditions via variational calculus) shows that exact stationarity implies exact equilibrium only in the infinite-rationality limit. No explicit epsilon-Nash bound is derived that relates the free-energy residual or rationality parameter to payoff deviation or total-variation distance to equilibrium. This is load-bearing for the non-monotonic precision-influence prediction, as it leaves the 'approximate' regime qualitative and non-falsifiable in its current form.

    Authors: We appreciate the referee's observation regarding the Nash correspondence. The current analysis demonstrates that stationary points of the collective free energy correspond to Nash equilibria under the assumption of unbounded rationality, with the bounded case yielding approximations. However, we concur that an explicit quantitative bound is essential for rigor and falsifiability. Accordingly, we will revise the manuscript to include a derivation of an epsilon-Nash bound. Specifically, we will show that the free-energy residual is bounded by a term proportional to the rationality parameter times the payoff deviation, using the properties of the variational free energy and the definition of the induced game. This will directly support the non-monotonic precision-influence prediction by quantifying the approximation error as a function of the parameters. We believe this addition will address the concern and strengthen the theoretical foundation. revision: yes

  2. Referee: [Empirical validation and predictive theory of cooperation] The falsifiable prediction of a non-monotonic relationship between sensory precision and agent influence depends on the definition and selection of the precision parameter (a free parameter in the model). The empirical validation across systems provides no details on error analysis, exclusion criteria, or robustness to alternative operationalizations of precision, undermining the claim that the relationship is a genuine, parameter-independent prediction.

    Authors: We thank the referee for pointing out the need for greater transparency in the empirical validation. While the manuscript presents the non-monotonic relationship as a prediction of the theory, we acknowledge that the current presentation lacks sufficient methodological details. In the revised version, we will add a dedicated subsection on empirical methods that specifies: the precise definitions of sensory precision used in each system studied; comprehensive error analysis, including standard errors and statistical significance tests for the observed non-monotonicity; the criteria used for including or excluding data points or systems; and results from robustness checks employing alternative operationalizations of precision (e.g., varying the scaling factor or using different proxies). These enhancements will confirm that the predicted relationship is robust and not sensitive to specific parameter choices, thereby reinforcing the predictive power of the framework. revision: yes

Circularity Check

0 steps flagged

No significant circularity in the derivation chain.

full rationale

The manuscript introduces a collective free-energy functional and derives its stationary conditions under explicit assumptions of bounded rationality and local information constraints. It then states a correspondence to approximate Nash equilibria in an induced game and a converse variational representation for a class of cooperative games. These steps are presented as proofs rather than redefinitions; the induced game and Gibbs-coalition representation are constructed from the variational setup but the paper treats the mapping as a derived equivalence rather than an identity by fiat. The non-monotonic precision-influence relationship is obtained from the same stationary conditions and is offered as a falsifiable prediction that is subsequently checked against external data sets (neural, biological, artificial). No equation is shown to equal its own input by algebraic rearrangement, no parameter is fitted on a subset and then relabeled a prediction, and no load-bearing step rests solely on a self-citation whose content is itself unverified. The framework therefore remains self-contained against the benchmarks supplied in the text.

Axiom & Free-Parameter Ledger

1 free parameters · 2 axioms · 2 invented entities

The central claim rests on domain assumptions of bounded rationality and local information constraints, introduces new conceptual entities without independent falsifiable handles in the abstract, and offers predictions whose independence from parameter choices cannot be verified without the full derivations.

free parameters (1)
  • sensory precision
    Appears in the non-monotonic relationship prediction between precision and agent influence; its role in validation is unspecified in the abstract.
axioms (2)
  • domain assumption Bounded rationality
    Invoked to establish that stationary points of collective free energy correspond to approximate Nash equilibria.
  • domain assumption Local information constraints
    Required for the correspondence between collective free-energy stationary points and induced-game equilibria.
invented entities (2)
  • Game-Theoretic Free Energy Principle no independent evidence
    purpose: Unified variational framework linking multi-agent free-energy minimization to stochastic games and Nash equilibria
    New principle introduced in the abstract as the core contribution.
  • free-energy formulation of the Harsanyi dividend no independent evidence
    purpose: Characterize higher-order irreducible multi-agent synergy
    New formulation introduced to handle higher-order effects.

pith-pipeline@v0.9.0 · 5504 in / 1734 out tokens · 71087 ms · 2026-05-07T06:52:48.935243+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. A Game Theoretic Free Energy Analysis of Higher Order Synergy in Attention Heads of Large Language Models

    cs.AI 2026-05 unverdicted novelty 4.0

    Attention heads exhibit negative higher-order synergy (negative triple dividends), allowing pruning of redundant heads that cuts FLOPs by ~18% with only small perplexity increase.

Reference graph

Works this paper leans on

39 extracted references · 4 canonical work pages · cited by 1 Pith paper

  1. [1]

    Pati˜ no Padial, S

    T. Pati˜ no Padial, S. Chen, A. C. Hortel˜ ao, et al. Swarming intelligence in self-propelled micromotors and nanomotors.Nature Reviews Materials, 10:947–963, 2025

    2025

  2. [2]

    Hyperedge overlap drives explosive transitions in systems with higher-order in- teractions.Nature Communications, 16:555, 2025

    Fabrizio Malizia, Santiago Lamata-Ot´ ın, Mattia Frasca, Alex Arenas, and Jes´ us G´ omez- Garde˜ nes. Hyperedge overlap drives explosive transitions in systems with higher-order in- teractions.Nature Communications, 16:555, 2025

    2025

  3. [3]

    A free energy principle for the brain.Journal of Physiology - Paris, 100(1-3):70–87, Jul-Sep 2006

    Karl Friston, James Kilner, and Lee Harrison. A free energy principle for the brain.Journal of Physiology - Paris, 100(1-3):70–87, Jul-Sep 2006

    2006

  4. [4]

    Variational free energy and the laplace approximation.NeuroImage, 34(1):220–234, 2007

    Karl Friston, J´ er´ emie Mattout, Nelson Trujillo-Barreto, John Ashburner, and Will Penny. Variational free energy and the laplace approximation.NeuroImage, 34(1):220–234, 2007

    2007

  5. [5]

    The free-energy principle: a unified brain theory?Nature Reviews Neuro- science, 11(2):127–138, 2010

    Karl Friston. The free-energy principle: a unified brain theory?Nature Reviews Neuro- science, 11(2):127–138, 2010

    2010

  6. [6]

    Blei, Alp Kucukelbir, and Jon D

    David M. Blei, Alp Kucukelbir, and Jon D. McAuliffe. Variational inference: A review for statisticians.Journal of the American Statistical Association, 112(518):859–877, 2017

    2017

  7. [7]

    Shafiei, H

    A. Shafiei, H. Jesawada, K. Friston, et al. Distributionally robust free energy principle for decision-making.Nature Communications, 17:707, 2026

    2026

  8. [8]

    John F. Nash. Equilibrium points in n-person games.Proceedings of the National Academy of Sciences, 36(1):48–49, 1950

    1950

  9. [9]

    John F. Nash. Non-cooperative games.Annals of Mathematics, 54(2):286–295, 1951

    1951

  10. [10]

    Sequential causal normal form games: Theory, computation, and strategic signaling.arXiv preprint arXiv:2511.06934, 2025

    Dennis Thumm. Sequential causal normal form games: Theory, computation, and strategic signaling.arXiv preprint arXiv:2511.06934, 2025. AAAI 2026 Workshop on Foundations of Agentic Systems Theory

    work page arXiv 2025

  11. [11]

    Re- designing deep neural networks: Bridging game theory and statistical physics.Neural Net- works, 191:107807, 2025

    Djamel Bouchaffra, Faycal Ykhlef, Bilal Faye, Mustapha Lebbah, and Hanene Azzag. Re- designing deep neural networks: Bridging game theory and statistical physics.Neural Net- works, 191:107807, 2025

    2025

  12. [12]

    Game theory meets statistical physics: A novel deep neural networks design.IEEE Transactions on Cybernetics, Jan 2026

    Djamel Bouchaffra, Fay¸ cal Ykhlef, Bilal Faye, Mustapha Lebbah, and Hanane Azzag. Game theory meets statistical physics: A novel deep neural networks design.IEEE Transactions on Cybernetics, Jan 2026

    2026

  13. [13]

    Interactive exploration of cnn interpretability via coalitional game theory

    Lei Yang, Lingmeng Lu, Chao Liu, Jian Zhang, Kehua Guo, Fangfang Zhou, Ying Zhao, and Ning Zhang. Interactive exploration of cnn interpretability via coalitional game theory. Scientific Reports, 15:9261, 2025

    2025

  14. [14]

    Harsanyi

    John C. Harsanyi. A simplified bargaining model for the n-person cooperative game.Inter- national Economic Review, 4(2):194–220, 1963. 19

    1963

  15. [15]

    Harsanyi

    John C. Harsanyi. Games with incomplete information played by bayesian players.Man- agement Science, 14(3):159–182, 1967

    1967

  16. [16]

    Harsanyi and Reinhard Selten

    John C. Harsanyi and Reinhard Selten. A generalized nash solution for two-person bargain- ing games with incomplete information.Management Science, 18(5-part-2):80–106, 1972

    1972

  17. [17]

    Groundbreaking study reveals how topology drives complexity in brain, climate, and ai

    Queen Mary University of London. Groundbreaking study reveals how topology drives complexity in brain, climate, and ai. ScienceDaily, February 2025. Accessed: 2025-04-29

    2025

  18. [18]

    Q-learning-driven adaptive rewiring for cooperative control in heterogeneous networks.arXiv preprint, arXiv:2509.01057, 2025

    Yi-Ning Weng and Hsuan-Wei Lee. Q-learning-driven adaptive rewiring for cooperative control in heterogeneous networks.arXiv preprint, arXiv:2509.01057, 2025. Submitted to Physics and Society (physics.soc-ph)

    work page arXiv 2025

  19. [19]

    Neu- rogame transformer: Gibbs-inspired attention driven by game theory and statistical physics

    Djamel Bouchaffra, Faycal Ykhlef, Hanene Azzag, Mustapha Lebbah, and Bilal Faye. Neu- rogame transformer: Gibbs-inspired attention driven by game theory and statistical physics. arXiv preprint, arXiv:2603.18761, 2025. Submitted to IEEE Transactions on Cybernetics

    work page arXiv 2025

  20. [20]

    Lloyd S. Shapley. A value for n-person games. In Harold W. Kuhn and Albert W. Tucker, ed- itors,Contributions to the Theory of Games, volume 2, pages 307–317. Princeton University Press, 1953

    1953

  21. [21]

    Lundberg and Su-In Lee

    Scott M. Lundberg and Su-In Lee. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, volume 30, pages 4765–4774, 2017

    2017

  22. [22]

    Couzin, Jens Krause, Nigel R

    Iain D. Couzin, Jens Krause, Nigel R. Franks, and Simon A. Levin. Effective leadership and decision-making in animal groups on the move.Nature, 433:513–516, 2005

    2005

  23. [23]

    Tractable multi-agent reinforcement learning through behavioral economics

    Eric Mazumdar, Kishan Panaganti, and Laixi Shi. Tractable multi-agent reinforcement learning through behavioral economics. InProceedings of the International Conference on Learning Representations (ICLR), 2025

    2025

  24. [24]

    Mill´ an, Hanlin Sun, Lorenzo Giambagli, Riccardo Muolo, Timoteo Carletti, Joaqu´ ın J

    Ana P. Mill´ an, Hanlin Sun, Lorenzo Giambagli, Riccardo Muolo, Timoteo Carletti, Joaqu´ ın J. Torres, Filippo Radicchi, J¨ urgen Kurths, and Ginestra Bianconi. Topology shapes dynamics of higher-order networks.Nature Physics, 2025

    2025

  25. [25]

    A perspective on judgment and choice: Mapping bounded rationality

    Daniel Kahneman. A perspective on judgment and choice: Mapping bounded rationality. American Psychologist, 58(9):697–720, 2003

    2003

  26. [26]

    Herbert A. Simon. A behavioral model of rational choice.Quarterly Journal of Economics, 69(1):99–118, 1955

    1955

  27. [27]

    Networks beyond pairwise interactions: Structure and dynamics.Physics Reports, 874:1–92, 2020

    Federico Battiston, Giulia Cencetti, Iacopo Iacopini, Vito Latora, Maxime Lucas, Alice Patania, Jean-Gabriel Young, and Giovanni Petri. Networks beyond pairwise interactions: Structure and dynamics.Physics Reports, 874:1–92, 2020

    2020

  28. [28]

    Synaptic reverberation underlying mnemonic persistent activity.Trends in Neurosciences, 24(8):455–463, 2001

    Xiao-Jing Wang. Synaptic reverberation underlying mnemonic persistent activity.Trends in Neurosciences, 24(8):455–463, 2001

    2001

  29. [29]

    J. M. Keegstra, F. Avgidis, E. Usher, Y. Mulla, J. S. Parkinson, and T. S. Shimizu. Spon- taneous switching in a protein signalling array reveals near-critical cooperativity.Nature Physics, 22:452–460, 2026

    2026

  30. [30]

    Addison- Wesley, 1972

    Nigel Goldenfeld.Lectures on Phase Transitions and the Renormalization Group. Addison- Wesley, 1972

    1972

  31. [31]

    Higher-order ising model on hypergraphs.Physical Review E, 112:L022301, Aug 2025

    Thomas Robiglio, Leonardo Di Gaetano, Ada Altieri, Giovanni Petri, and Federico Bat- tiston. Higher-order ising model on hypergraphs.Physical Review E, 112:L022301, Aug 2025. 20

    2025

  32. [32]

    Martin Burger, Samira Kabri, Yury Korolev, Tim Roith, and Lukas Weigand. Analysis of mean-field models arising from self-attention dynamics in transformer architectures with layer normalization.Philosophical Transactions of the Royal Society A, 383(2298):20240233, 2025

    2025

  33. [33]

    Gomez, Lukasz Kaiser, and Illia Polosukhin

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, and Illia Polosukhin. Attention is all you need. InAdvances in Neural Information Processing Systems, volume 30, pages 5998–6008, 2017

    2017

  34. [34]

    McClelland

    Shaunak Bhandarkar and James L. McClelland. Neural computation without slots: Steps towards biologically plausible memory and attention in natural and artificial intelligence. arXiv preprint, arXiv:2511.04593, 2025

    work page arXiv 2025

  35. [35]

    Luppi, Yonatan Sanz Perl, Jakub Vohryzek, Hana Ali, Pedro A

    Andrea I. Luppi, Yonatan Sanz Perl, Jakub Vohryzek, Hana Ali, Pedro A. M. Mediano, Fernando E. Rosas, Filip Milisav, Laura E. Su´ arez, Silvia Gini, Daniel Gutierrez-Barragan, Yohan Yee, Se´ an Froudist-Walsh, Alessandro Gozzi, Bratislav Misic, Gustavo Deco, and Morten L. Kringelbach. Competitive interactions shape mammalian brain network dynamics and com...

    2026

  36. [36]

    Hein, Sara Brin Rosenthal, George I

    Andrew M. Hein, Sara Brin Rosenthal, George I. Hagstrom, Andrew Berdahl, Colin J. Torney, and Iain D. Couzin. The evolution of distributed sensing and collective computation in animal populations.eLife, 4:e10955, 2015

    2015

  37. [37]

    Addison-Wesley, 1988

    Giorgio Parisi.Statistical Field Theory. Addison-Wesley, 1988

    1988

  38. [38]

    Ball, Thomas Parr, and Karl J

    Noor Sajid, Philip J. Ball, Thomas Parr, and Karl J. Friston. Active inference: demystified and compared.Neural Computation, 33(3):674–712, 2021

    2021

  39. [39]

    Satisficing equilibrium

    Bary Pradelski and Bassel Tarbush. Satisficing equilibrium. InProceedings of the 26th ACM Conference on Economics and Computation, EC ’25, page 442, New York, NY, USA, 2025. Association for Computing Machinery. 21

    2025