A potentialization algorithm for games with applications to multi-agent learning in repeated games
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914342241304576 |
|---|---|
| author | Lakheshar, Philipp Rezagholi, Sharwin |
| author_facet | Lakheshar, Philipp Rezagholi, Sharwin |
| contents | We investigate an algorithm that assigns to any game in normal form an approximating game that admits an ordinal potential function. Due to the properties of potential games, the algorithm equips every game with a surrogate reward structure that allows efficient multi-agent learning. Numerical simulations using the replicator dynamics show that 'potentialization' guarantees convergence to stable agent behavior. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18925 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A potentialization algorithm for games with applications to multi-agent learning in repeated games Lakheshar, Philipp Rezagholi, Sharwin Multiagent Systems Computer Science and Game Theory We investigate an algorithm that assigns to any game in normal form an approximating game that admits an ordinal potential function. Due to the properties of potential games, the algorithm equips every game with a surrogate reward structure that allows efficient multi-agent learning. Numerical simulations using the replicator dynamics show that 'potentialization' guarantees convergence to stable agent behavior. |
| title | A potentialization algorithm for games with applications to multi-agent learning in repeated games |
| topic | Multiagent Systems Computer Science and Game Theory |
| url | https://arxiv.org/abs/2602.18925 |