Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances
Not on the map. Why?
Abstract (arXiv)
Recent research studies communication emergence in communities of deep network agents assigned a joint task, hoping to gain insights on human language evolution. We propose here a new task capturing crucial aspects of the human environment, such as natural object affordances, and of human conversation, such as full symmetry among the participants. By conducting a thorough pragmatic and semantic analysis of the emergent protocol, we show that the agents solve the shared task through genuine bilateral, referential communication. However, the agents develop multiple idiolects, which makes us conclude that full symmetry is not a sufficient condition for a common language to emerge.
Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 28 May 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 4; 2022: 1; 2023: 3; 2024: 2; 2025: 0; 2026: 1.
11 papers.
- 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Surveycited by 130
- 2024A Review of the Applications of Deep Learning-Based Emergent Communicationcited by 17
- 2021The Emergence of the Shape Bias Results from Communicative Efficiencycited by 13
- 2023Towards More Human-like AI Communication: A Review of Emergent Communication Researchcited by 13
- 2021Dynamic population-based meta-learning for multi-agent communication with natural languagecited by 10
- 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMscited by 10
- 2023Metropolis-Hastings algorithm in joint-attention naming game: Experimental semiotics studycited by 5
- 2022Over-communicate no more: Situated RL agents learn concise communication protocolscited by 4
- 2021PatchGame: Learning to Signal Mid-level Patches in Referential Gamescited by 3
- 2023Control as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learningcited by 3
- 2024A Combinatorial Approach to Neural Emergent Communicationcited by 1
- 2026The Five Ws of Multi-Agent Communication: Who Talks to Whom, When, What, and Why -- A Survey from MARL to Emergent Language and LLMs12 Feb 2026
- 2024A Combinatorial Approach to Neural Emergent Communication24 Oct 2024
- 2024A Review of the Applications of Deep Learning-Based Emergent Communication3 Jul 2024
- 2023Towards More Human-like AI Communication: A Review of Emergent Communication Research1 Aug 2023
- 2023Control as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learning11 Jul 2023
- 2023Metropolis-Hastings algorithm in joint-attention naming game: Experimental semiotics study31 May 2023
- 2022Over-communicate no more: Situated RL agents learn concise communication protocols2 Nov 2022
- 2021PatchGame: Learning to Signal Mid-level Patches in Referential Games2 Nov 2021
- 2021Dynamic population-based meta-learning for multi-agent communication with natural language27 Oct 2021
- 2021The Emergence of the Shape Bias Results from Communicative Efficiency13 Sep 2021
- 2021Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey10 May 2021