Diegetic Representation of Feedback in Open Games
From MaRDI portal
Publication:6150152
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 reverse-mode differentiation, 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.
Recommendations
Cites work
- scientific article; zbMATH DE number 1233801 (Why is no real title available?)
- scientific article; zbMATH DE number 7650831 (Why is no real title available?)
- 2-Dimensional Categories
- A compositional treatment of iterated open games
- Categorical foundations of gradient-based learning
- Compositional game theory
- Double categories of open dynamical systems (extended abstract)
- Essentials of game theory. A concise, multidisciplinary introduction.
- Games with Incomplete Information Played by “Bayesian” Players, I–III Part I. The Basic Model
- Higher-order decision theory
- Homotopy type theory: the logic of space
- Morphisms of open games
This page was built for publication: Diegetic Representation of Feedback in Open Games
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6150152)