Search Results for author: Federico Cacciamani

Found 4 papers, 0 papers with code

Multi-Agent Coordination in Adversarial Environments through Signal Mediated Strategies

no code implementations9 Feb 2021 Federico Cacciamani, Andrea Celli, Marco Ciccone, Nicola Gatti

Team members can coordinate their strategies before the beginning of the game, but are unable to communicate during the playing phase of the game.

Exploiting Opponents Under Utility Constraints in Sequential Games

no code implementations NeurIPS 2021 Martino Bernasconi-de-Luca, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Alberto Marchesi, Francesco Trovò

Recently, game-playing agents based on AI techniques have demonstrated super-human performance in several sequential games, such as chess, Go, and poker.

Public Information Representation for Adversarial Team Games

no code implementations25 Jan 2022 Luca Carminati, Federico Cacciamani, Marco Ciccone, Nicola Gatti

Interestingly, we show that our game is more expressive than the original extensive-form game as any state/action abstraction of the extensive-form game can be captured by our representation, while the reverse does not hold.

A Marriage between Adversarial Team Games and 2-player Games: Enabling Abstractions, No-regret Learning, and Subgame Solving

no code implementations18 Jun 2022 Luca Carminati, Federico Cacciamani, Marco Ciccone, Nicola Gatti

This work shows that we can recover from this weakness by bridging the gap between sequential adversarial team games and 2-player games.

Cannot find the paper you are looking for? You can Submit a new open access paper.