The Hanabi Challenge: A New Frontier for AI Research (2019-02-02T00:00:00.000000Z)

TL;DR

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.

Authors

H. Larochelle

18 papers

H. F. Song

4 papers

Marc G. Bellemare

8 papers

Marc Lanctot

7 papers

Vincent Dumoulin

7 papers

Jakob N. Foerster

8 papers

Emilio Parisotto

3 papers

Iain Dunning

3 papers

A. Chandar

4 papers

Nolan Bard

2 papers

Neil Burch

2 papers

Subhodeep Moitra

1 papers

Edward Hughes

1 papers

Shibl Mourad

1 papers

Michael H. Bowling

1 papers

TL;DR

Authors

References92 items

Practical Specification of Belief Manipulation in Games

Implicit Communication of Actionable Information in Human-AI teams

Re-determinizing Information Set Monte Carlo Tree Search in Hanabi

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play

Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning

A survey and critique of multiagent deep reinforcement learning

Dopamine: A Research Framework for Deep Reinforcement Learning

Evolving Agents for the Hanabi 2018 CIG Competition

Human-level performance in 3D multiplayer games with population-based reinforcement learning

Learning Policy Representations in Multiagent Systems

Time and Space: Why Imperfect Information Games are Hard

Machine Theory of Mind

Emergent Communication through Negotiation

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

Superhuman AI for heads-up no-limit poker: Libratus beats top professionals

Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm

Population Based Training of Neural Networks

A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning

Mastering the game of Go without human knowledge

Rainbow: Combining Improvements in Deep Reinforcement Learning

Autonomous agents modelling other agents: A comprehensive survey and open problems

Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents

Learning with Opponent-Learning Awareness

A Distributional Perspective on Reinforcement Learning

Playing Hanabi Near-Optimally

Deal or No Deal? End-to-End Learning of Negotiation Dialogues

Evaluating and modelling Hanabi-playing agents

DeepStack: Expert-level artificial intelligence in heads-up no-limit poker

DeepMind Lab

GuessWhat?! Visual Object Discovery through Multi-modal Dialogue

Aspects of the Cooperative Card Game Hanabi

Multi-Agent Cooperation and the Emergence of (Natural) Language

Automatic Bridge Bidding Using Deep Reinforcement Learning

Opponent Modeling in Deep Reinforcement Learning

OpenAI Gym

Learning Multiagent Communication with Backpropagation

Learning to Communicate with Deep Multi-Agent Reinforcement Learning

Hanabi is NP-complete, Even for Cheaters who Look at Their Cards

Asynchronous Methods for Deep Reinforcement Learning

Mastering the game of Go with deep neural networks and tree search

How to Make the Perfect Fireworks Display: Two Strategies for Hanabi

Prioritized Experience Replay

Solving Hanabi: Estimating Hands by Opponent's Actions in Cooperative Game with Incomplete Information

Human-level control through deep reinforcement learning

Heads-up limit hold’em poker is solved

Predicting human behavior in unrepeated, simultaneous-move games

Solving Imperfect Information Games Using Decomposition

The Arcade Learning Environment: An Evaluation Platform for General Agents

Predicting Pragmatic Reasoning in Language Games

Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems

The communicative function of ambiguity in language

Ad Hoc Autonomous Agent Teams: Collaboration without Pre-Coordination

Bootstrapping from Game Tree Search

Game Theory of Mind

A Comprehensive Survey of Multiagent Reinforcement Learning

Regret Minimization in Games with Incomplete Information

Bandit Based Monte-Carlo Planning

Cooperative Multi-Agent Learning: The State of the Art

Coordination and Adaptation in Impromptu Teams

A Framework for Sequential Planning in Multi-Agent Settings

Simultaneous Adversarial Multi-Robot Learning

Deep Blue

The Complexity of Decentralized Control of Markov Decision Processes

KnightCap: A chess program that learns by combining TD(lambda) with game-tree search

CHINOOK: The World Man-Machine Checkers Champion

Temporal Difference Learning and TD-Gammon

Markov Games as a Framework for Multi-Agent Reinforcement Learning

STRATEGIC INFORMATION TRANSMISSION

Does the chimpanzee have a theory of mind?

Impala

The Hanabi Learning Environment

I See What You See: Integrating Eye Tracking into Hanabi Playing Agents

Conventions for hanabi

Github - lightvector/fireflower: A rewrite of hanabi-bot in scala

: Hanabi simulation in rust

Reinforcement learning - an introduction, 2nd Edition

Github - wuthefwasthat/hanabi.rs: Hanabi simulation in rust, https://github.com/ WuTheFWasThat/hanabi.rs, [Online; accessed 29-November-2018] (2018)