# Reinforcement Learning for Hanabi

arXiv: https://arxiv.org/abs/2506.00458 · HTML: https://mlsanity.com/paper/2506.00458/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods.
- Builds on 2 of its 5 references that are in the map.
- First posted on arXiv 31 May 2025.

## Placed in

- Deep reinforcement learning methods / [RL for games and combinatorial optimization](https://mlsanity.com/deeprl/rl-for-games-and-combinatorial-optimization/)

## Builds on (most cited first, 2 of 2)

- [Imitation Learning by Reinforcement Learning](https://mlsanity.com/paper/2108.04763/) (2021)
- [Instructive artificial intelligence (AI) for human training, assistance, and explainability](https://mlsanity.com/paper/2111.01726/) (2021)

## Built on by (most cited first, 1 of 1)

- [The Convention Gap: Beyond Literal Content in Human-AI Cooperation](https://mlsanity.com/paper/2609.11489/) (2026)

## Abstract (arXiv)

Hanabi has become a popular game for research when it comes to reinforcement learning (RL) as it is one of the few cooperative card games where you have incomplete knowledge of the entire environment, thus presenting a challenge for a RL agent. We explored different tabular and deep reinforcement learning algorithms to see which had the best performance both against an agent of the same type and also against other types of agents. We establish that certain agents played their highest scoring games against specific agents while others exhibited higher scores on average by adapting to the opposing agent's behavior. We attempted to quantify the conditions under which each algorithm provides the best advantage and identified the most interesting interactions between agents of different types. In the end, we found that temporal difference (TD) algorithms had better overall performance and balancing of play types compared to tabular agents. Specifically, tabular Expected SARSA and deep Q-Learning agents showed the best performance.