playing-games-7

Game of Hanabi

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in game-of-hanabi-7

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find game-of-hanabi-7 models and implementations

Datasets

Hanabi Learning Environment

Subtasks

No subtasks available.

Most implemented papers

Improving Policies via Search in Cooperative Partially Observable Games

Adam Lerer, Jakob N. Foerster, Hengyuan Hu, Noam Brown•Wed Dec 04 2019

This paper proposes two different search techniques that can be applied to improve an arbitrary agreed-upon policy in a cooperative partially observable game and proves that these search procedures are theoretically guaranteed to at least maintain the original performance of the agreed-Upon policy (up to a bounded approximation error).

84

Content

0

Paper Graph

The Hanabi Challenge: A New Frontier for AI Research

H. Larochelle, H. F. Song, Marc G. Bellemare, Marc Lanctot, Vincent Dumoulin, Jakob N. Foerster, Emilio Parisotto, Iain Dunning, A. Chandar, Nolan Bard, Neil Burch, Subhodeep Moitra, Edward Hughes, Shibl Mourad, Michael H. Bowling•Fri Feb 01 2019

It is argued that Hanabi elevates reasoning about the beliefs and intentions of other agents to the foreground and developing novel techniques for such theory of mind reasoning will not only be crucial for success in Hanabi, but also in broader collaborative efforts, especially those with human partners.

397 0

Paper Graph

Towards Few-shot Coordination: Revisiting Ad-hoc Teamplay Challenge In the Game of Hanabi

Sarath Chandar, Janarthanan Rajendran, Hadi Nekoei, Xutong Zhao, Miao Liu•Sat Aug 19 2023

This work formally defined a framework based on a popular cooperative multi-agent game called Hanabi to evaluate the adaptability of MARL methods and defined a new metric called adaptation regret that measures the agent's ability to efficiently adapt and improve its coordination performance when paired with some held-out pool of partners on top of its ZSC performance.

10 0

Paper Graph

Adding a benchmark result helps the community track progress.