mlsanityData to 14 Oct 2026

Reinforcement Learning for Hanabi

arXiv 2506.00458 ↗First posted 31 May 2025cs.LG cs.AI cs.GTcited by 1

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

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.

Key facts. Cited by 1 paper 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.

Builds on

2 of 5 references.

References · 2

  1. 2021Imitation Learning by Reinforcement Learningcited by 17
  2. 2021Instructive artificial intelligence (AI) for human training, assistance, and explainabilitycited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026The Convention Gap: Beyond Literal Content in Human-AI Cooperationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025A Generalist Hanabi Agent
  2. 2024Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi
  3. 2026Deep Reinforcement Learning to Master the Asymmetric Strategy of Baghchal
  4. 2024A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges
  5. 2021Reinforcement Learning In Two Player Zero Sum Simultaneous Action Games
  6. 2024Efficient Exploration in Deep Reinforcement Learning: A Novel Bayesian Actor-Critic Algorithm
  7. 2026Test-time Reinforcement Learning in Imperfect Information Games
  8. 2025Deep Reinforcement Learning Xiangqi Player with Monte Carlo Tree Search