Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2604.18123 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914491536506880 |
|---|---|
| author | Sriraman, Abhishek Vasilaki, Eleni Loftin, Robert |
| author_facet | Sriraman, Abhishek Vasilaki, Eleni Loftin, Robert |
| contents | Ad-hoc collaboration often relies on identifying and adhering to shared conventions. However, when partners can follow multiple conventions, agents must do more than simply adapt; they must actively steer the team toward the most effective joint strategy. We present ConventionPlay, a reinforcement learning-based approach that extends cognitive hierarchies to include a diverse population of adaptive followers. By training against partners with varied capability limits, our agent learns to probe its partner's repertoire, leading the team when possible and following when necessary. Our results in canonical coordination tasks show that ConventionPlay achieves superior coordination efficiency, particularly in settings where conventions have differentiated payoffs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18123 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ConventionPlay: Capability-Limited Training for Robust Ad-Hoc Collaboration Sriraman, Abhishek Vasilaki, Eleni Loftin, Robert Multiagent Systems Ad-hoc collaboration often relies on identifying and adhering to shared conventions. However, when partners can follow multiple conventions, agents must do more than simply adapt; they must actively steer the team toward the most effective joint strategy. We present ConventionPlay, a reinforcement learning-based approach that extends cognitive hierarchies to include a diverse population of adaptive followers. By training against partners with varied capability limits, our agent learns to probe its partner's repertoire, leading the team when possible and following when necessary. Our results in canonical coordination tasks show that ConventionPlay achieves superior coordination efficiency, particularly in settings where conventions have differentiated payoffs. |
| title | ConventionPlay: Capability-Limited Training for Robust Ad-Hoc Collaboration |
| topic | Multiagent Systems |
| url | https://arxiv.org/abs/2604.18123 |