Dibbla: This file/list contains several papers about Hanabi, but mostly focus on 2 ideas: MCTS method and learning a protocol.
Theoretical Method
Playing Hanabi Near-Optimally
This paper, from a theory view, provides a hat-guessing strategy that reaches nearly full score in some settings. Check here.
Survey
The Hanabi challenge: A new frontier for AI research
Check here
The 2018 Hanabi Competition
Check here
MCTS
Re-determinizing MCTS in Hanabi
Check here
Information Set Monte Carlo Tree Search
Where the IS-MCTS was proposed. Check here
Multi-objective Monte-Carlo Tree Search
This actually fails in Hanabi. Check here
Monte-Carlo tree search for constrained POMDPs
Check here
Evaluating and modelling Hanabi-playing agents
Check here
Learning a protocol / Recent Advance
Communicating via Markov Decision Processes
Check here
Off-Belief Learning
By Foerster. Check here
“Other-Play” for Zero-Shot Coordination
Check here
Multi-agent common knowledge reinforcement learning
Check here