The Hanabi challenge: a new frontier for AI research
DOI10.1016/j.artint.2019.103216zbMath1476.68223arXiv1902.00506OpenAlexW2913781869WikidataQ126655125 ScholiaQ126655125MaRDI QIDQ2302288
Edward Hughes, Nolan Bard, Marc G. Bellemare, H. Francis Song, Hugo Larochelle, Emilio Parisotto, Marc Lanctot, Subhodeep Moitra, Neil Burch, Michael Bowling, Iain Dunning, Sarath Chandar, Jakob N. Foerster, Vincent Dumoulin, Shibl Mourad
Publication date: 26 February 2020
Published in: Artificial Intelligence (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1902.00506
communicationcooperative gamesreinforcement learninggamesimperfect informationmulti-agent learningtheory of mindchallenge paper
Learning and adaptive systems in artificial intelligence (68T05) Cooperative games (91A12) General topics in artificial intelligence (68T01) Combinatorial games (91A46) Agent technology and artificial intelligence (68T42)
Related Items (3)
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Hanabi is NP-hard, even for cheaters who look at their cards
- Autonomous agents modelling other agents: a comprehensive survey and open problems
- Predicting human behavior in unrepeated, simultaneous-move games
- Evolutionary Dynamics of Multi-Agent Learning: A Survey
- How to Make the Perfect Fireworks Display: Two Strategies forHanabi
- Predicting Pragmatic Reasoning in Language Games
- Multiagent Systems
- Strategic Information Transmission
- Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents
- DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
- Superhuman AI for heads-up no-limit poker: Libratus beats top professionals
- A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
- The Complexity of Decentralized Control of Markov Decision Processes
- Deep Blue
This page was built for publication: The Hanabi challenge: a new frontier for AI research