A Minimax Approach to Ad Hoc Teamwork
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912219496710144 |
|---|---|
| author | Villin, Victor Buening, Thomas Kleine Dimitrakakis, Christos |
| author_facet | Villin, Victor Buening, Thomas Kleine Dimitrakakis, Christos |
| contents | We propose a minimax-Bayes approach to Ad Hoc Teamwork (AHT) that optimizes policies against an adversarial prior over partners, explicitly accounting for uncertainty about partners at time of deployment. Unlike existing methods that assume a specific distribution over partners, our approach improves worst-case performance guarantees. Extensive experiments, including evaluations on coordinated cooking tasks from the Melting Pot suite, show our method's superior robustness compared to self-play, fictitious play, and best response learning. Our work highlights the importance of selecting an appropriate training distribution over teammates to achieve robustness in AHT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_02377 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Minimax Approach to Ad Hoc Teamwork Villin, Victor Buening, Thomas Kleine Dimitrakakis, Christos Artificial Intelligence We propose a minimax-Bayes approach to Ad Hoc Teamwork (AHT) that optimizes policies against an adversarial prior over partners, explicitly accounting for uncertainty about partners at time of deployment. Unlike existing methods that assume a specific distribution over partners, our approach improves worst-case performance guarantees. Extensive experiments, including evaluations on coordinated cooking tasks from the Melting Pot suite, show our method's superior robustness compared to self-play, fictitious play, and best response learning. Our work highlights the importance of selecting an appropriate training distribution over teammates to achieve robustness in AHT. |
| title | A Minimax Approach to Ad Hoc Teamwork |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2502.02377 |