Inductive Bias for Emergent Communication in a Continuous Setting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929561465257984 |
|---|---|
| author | Villanger, John Isak Fjellvang Bojesen, Troels Arnfred |
| author_facet | Villanger, John Isak Fjellvang Bojesen, Troels Arnfred |
| contents | We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete symbols or continuous variables. We introduce an inductive bias to aid with the emergence of good communication protocols for continuous messages, and we look at the effect this type of inductive bias has for continuous and discrete messages in itself or when used in combination with reinforcement learning. We demonstrate that this type of inductive bias has a beneficial effect on the communication protocols learnt in two toy environments, Negotiation and Sequence Guess. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_03830 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Inductive Bias for Emergent Communication in a Continuous Setting Villanger, John Isak Fjellvang Bojesen, Troels Arnfred Machine Learning Artificial Intelligence Multiagent Systems I.2.11 We study emergent communication in a multi-agent reinforcement learning setting, where the agents solve cooperative tasks and have access to a communication channel. The communication channel may consist of either discrete symbols or continuous variables. We introduce an inductive bias to aid with the emergence of good communication protocols for continuous messages, and we look at the effect this type of inductive bias has for continuous and discrete messages in itself or when used in combination with reinforcement learning. We demonstrate that this type of inductive bias has a beneficial effect on the communication protocols learnt in two toy environments, Negotiation and Sequence Guess. |
| title | Inductive Bias for Emergent Communication in a Continuous Setting |
| topic | Machine Learning Artificial Intelligence Multiagent Systems I.2.11 |
| url | https://arxiv.org/abs/2306.03830 |