@inproceedings{d8b9954c57994213b6f8289e9bb9a175,
title = "Diegetic representation of feedback in open games",
abstract = "We improve the framework of open games with agency by showing how the players' counterfactual analysis giving rise to Nash equilibria can be described in the dynamics of the game itself (hence diegetically), getting rid of devices such as equilibrium predicates. This new approach overlaps almost completely with the way gradient-based learners are specified and trained. Indeed, we show feedback propagation in games can be seen as a form of backpropagation, with a crucial difference explaining the distinctive character of the phenomenology of non-cooperative games. We outline a functorial construction of arena of games, show players form a subsystem over it, and prove that their 'fixpoint behaviours' are Nash equilibria.",
keywords = "open games, Nash equilibria, gradient-based learners",
author = "Matteo Capucci",
year = "2023",
month = aug,
day = "7",
doi = "10.4204/eptcs.380.9",
language = "English",
volume = "380",
series = "Electronic Proceedings in Theoretical Computer Science",
publisher = "Open Publishing Association",
pages = "145--158",
editor = "Jade Master and Martha Lewis",
booktitle = "Proceedings Fifth International Conference on Applied Category Theory",
note = "5th International Conference on Applied Category Theory ; Conference date: 18-07-2022 Through 22-07-2022",
}