The value of information and the emergence of communication in evolved e-puck robots

Hugging Face Daily Papers Papers
evolutionary-robotics multi-agent-communication gru simulated-embodiment reinforcement-learning emergent-behavior

Summary

该论文研究了在PyBullet中重建的两只e-puck机器人之间通信行为的涌现条件，发现通信的出现与其所传递信息的价值成正比，而为孤立智能体设计的先天反射架构在社交任务中反而可能成为阻碍。

We study when communication emerges between autonomous agents and what role an innate action selection architecture plays. Two e-puck robots, reconstructed in PyBullet from their Webots model and validated against it, must find a feeding zone that can only be detected when a robot passes over it. Each robot can emit a one-bit signal whose direction is detected by the receiver. Control is provided by a GRU recurrent network with a residual path, either operating alone or as a channel within an Embedded Action Selection Architecture (EASA). Fitness measures only the time the robots spend over the food. When the robots receive a compass pointing to the food, use of the signal disappears completely. Without a compass, in a small arena, three independent runs achieved similar performance using different strategies: a referential signal, a permanent beacon, or no use of the signal. As the arena expands, the strategy based on a referential signal generalizes best. In contrast, evolving directly in the large arena does not increase the frequency of communication, but it does separate the strategies, and the referential signal clearly outperforms solitary searching. Within EASA, innate reflexes constrain the network and reduce performance. As its priorities evolve, evolution consistently weakens those reflexes. The results suggest that communication emerges in proportion to the value of the information it transmits, and that an innate scaffolding designed for isolated agents can be an impediment in a social task.
Original Article
View Cached Full Text

Cached at: 10/12/26, 06:54 AM

Paper page - The value of information and the emergence of communication in evolved e-puck robots

Source: https://huggingface.co/papers/2610.13118

Abstract

Westudywhencommunicationemergesbetweenautonomousagentsandwhatroleaninnateactionselectionarchitectureplays.Twoe-puckrobots,reconstructedinPyBulletfromtheirWebotsmodelandvalidatedagainstit,mustfindafeedingzonethatcanonlybedetectedwhenarobotpassesoverit.Eachrobotcanemitaone-bitsignalwhosedirectionisdetectedbythereceiver.ControlisprovidedbyaGRUrecurrentnetworkwitharesidualpath,eitheroperatingaloneorasachannelwithinanEmbeddedActionSelectionArchitecture(EASA).Fitnessmeasuresonlythetimetherobotsspendoverthefood.Whentherobotsreceiveacompasspointingtothefood,useofthesignaldisappearscompletely.Withoutacompass,inasmallarena,threeindependentrunsachievedsimilarperformanceusingdifferentstrategies:areferentialsignal,apermanentbeacon,ornouseofthesignal.Asthearenaexpands,thestrategybasedonareferentialsignalgeneralizesbest.Incontrast,evolvingdirectlyinthelargearenadoesnotincreasethefrequencyofcommunication,butitdoesseparatethestrategies,andthereferentialsignalclearlyoutperformssolitarysearching.WithinEASA,innatereflexesconstrainthenetworkandreduceperformance.Asitsprioritiesevolve,evolutionconsistentlyweakensthosereflexes.Theresultssuggestthatcommunicationemergesinproportiontothevalueoftheinformationittransmits,andthataninnatescaffoldingdesignedforisolatedagentscanbeanimpedimentinasocialtask.

View arXiv pageView PDFGitHub0Add to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.13118 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2610.13118 in a dataset README.md to link it from this page.

Spaces citing this paper1

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Evaluating the Transfer of Co-Evolved Communication from 2D to 3D Simulation

Hugging Face Daily Papers

该论文研究两个机器人智能体在二维离散环境中共同演化出的通信机制，在迁移到基于物理的三维模拟器后是否仍能保持其功能作用。结果显示通信信号主要作为辅助解堵机制而非导航引导，且更长的评估时长能持续提升性能。

@snowboat84: Continuing the discussion on applying physical models in AI. Today's Transformer uses attention to allow information at different positions in a sequence to interact, but this mixing is very likely lossy and irreversible. Independent pieces of information get blurred and lost as they mix, and it's impossible to precisely reverse-engineer the input from the output. What we want is a different kind of interaction...

X AI KOLs Timeline

The author discusses the problem of information loss and irreversibility caused by the Transformer's attention mechanism, and proposes drawing inspiration from the physical model of soliton propagation to design a reversible, zero-loss interaction layer as a direction for improving existing AI model architectures.

@snwiki238337: Almost everyone designing multi-agent systems unconsciously falls into the same mindset: you must select a central agent, or hard-code a fixed execution pipeline in advance. In traditional thinking, a team without a leader is just a loose pile of sand. But once you've run multi-agent systems in production, you'll realize this centralized architecture is actually very fragile.

X AI KOLs Timeline

A Harvard and MIT team propose MPT (Market-Based Post-Training), which jointly learns action policies and self-orchestration through a bidding mechanism in a decentralized agent swarm — no central coordinator needed. Experiments on embodied creation, robot navigation, and deep research tasks validate its significant advantages in scaling, resilience to node failures, and task transfer.