NfgTransformer: Equivariant Representation Learning for Normal-form Games
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913233630134272 |
|---|---|
| author | Liu, Siqi Marris, Luke Piliouras, Georgios Gemp, Ian Heess, Nicolas |
| author_facet | Liu, Siqi Marris, Luke Piliouras, Georgios Gemp, Ian Heess, Nicolas |
| contents | Normal-form games (NFGs) are the fundamental model of strategic interaction. We study their representation using neural networks. We describe the inherent equivariance of NFGs -- any permutation of strategies describes an equivalent game -- as well as the challenges this poses for representation learning. We then propose the NfgTransformer architecture that leverages this equivariance, leading to state-of-the-art performance in a range of game-theoretic tasks including equilibrium-solving, deviation gain estimation and ranking, with a common approach to NFG representation. We show that the resulting model is interpretable and versatile, paving the way towards deep learning systems capable of game-theoretic reasoning when interacting with humans and with each other. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_08393 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NfgTransformer: Equivariant Representation Learning for Normal-form Games Liu, Siqi Marris, Luke Piliouras, Georgios Gemp, Ian Heess, Nicolas Computer Science and Game Theory Normal-form games (NFGs) are the fundamental model of strategic interaction. We study their representation using neural networks. We describe the inherent equivariance of NFGs -- any permutation of strategies describes an equivalent game -- as well as the challenges this poses for representation learning. We then propose the NfgTransformer architecture that leverages this equivariance, leading to state-of-the-art performance in a range of game-theoretic tasks including equilibrium-solving, deviation gain estimation and ranking, with a common approach to NFG representation. We show that the resulting model is interpretable and versatile, paving the way towards deep learning systems capable of game-theoretic reasoning when interacting with humans and with each other. |
| title | NfgTransformer: Equivariant Representation Learning for Normal-form Games |
| topic | Computer Science and Game Theory |
| url | https://arxiv.org/abs/2402.08393 |