---
title: '‘<em>Hanabi</em> AI’ directory'
description: "Bibliography for directory <code>reinforcement-learning/imperfect-information/hanabi</code>, most recent first: 25 <a class='icon-not' href='/doc/reinforcement-learning/imperfect-information/hanabi/index#links'>annotations</a> (<a href='/doc/reinforcement-learning/imperfect-information/index' class='link-page link-tag directory-indexes-upwards link-annotated' data-link-icon='arrow-up-left' data-link-icon-type='svg' rel='tag' title='Link to parent directory'>parent</a>)."
created: 2020-11-26
modified: 2025-04-06
status: in progress
previous: /doc/reinforcement-learning/imperfect-information/diplomacy/index
next: /doc/reinforcement-learning/imperfect-information/poker/index
confidence: log
importance: 0
css-extension: dropcaps-not
index: True
backlink: False
...

# See Also

::: {#see-alsos .directory-indexes .columns}
-   [Parent ('*`hidden-information game`{=html}*' tag)](/doc/reinforcement-learning/imperfect-information/index "Link to parent directory 'doc/reinforcement-learning/imperfect-information/' (ascending)"){#_VXNPRziZ
    .link-annotated .link-tag .directory-indexes-upwards rel="tag"}
:::

# Links {.display-pop-not}

## `“JaxMARL: Multi-Agent RL Environments in JAX”, Rutherford et al 2023`{=html} {#rutherford-et-al-2023-section}

**[`JaxMARL: Multi-Agent RL Environments in JAX`{=html}](https://arxiv.org/abs/2311.10090 "'JaxMARL: Multi-Agent RL Environments in JAX', Rutherford et al 2023"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Human-AI Coordination via Human-Regularized Search and Learning”, Hu et al 2022`{=html} {#hu-et-al-2022-2-section}

**[`Human-AI Coordination via Human-Regularized Search and Learning`{=html}](https://arxiv.org/abs/2210.05125#facebook "'Human-AI Coordination via Human-Regularized Search and Learning', Hu et al 2022"){.link-annotated
.id-not .include-annotation link-icon="facebook" link-icon-type="svg"
link-icon-color="#1877f2"}**

## `“Is Vanilla Policy Gradient Overlooked? Analyzing Deep Reinforcement Learning for Hanabi”, Grooten et al 2022`{=html} {#grooten-et-al-2022-section}

**[`Is Vanilla Policy Gradient Overlooked? Analyzing Deep Reinforcement Learning for Hanabi`{=html}](https://arxiv.org/abs/2203.11656 "'Is Vanilla Policy Gradient Overlooked? Analyzing Deep Reinforcement Learning for Hanabi', Grooten et al 2022"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“On-The-Fly Strategy Adaptation for Ad-Hoc Agent Coordination”, Zand et al 2022`{=html} {#zand-et-al-2022-section}

**[`On-the-fly Strategy Adaptation for ad-hoc Agent Coordination`{=html}](https://arxiv.org/abs/2203.08015 "'On-the-fly Strategy Adaptation for ad-hoc Agent Coordination', Zand et al 2022"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination”, Lucas & Allen 2022`{=html} {#lucas-allen-2022-section}

**[`Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination`{=html}](https://arxiv.org/abs/2201.12436 "'Any-Play: An Intrinsic Augmentation for Zero-Shot Coordination', Lucas & Allen 2022"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Conditional Imitation Learning for Multi-Agent Games”, Shih et al 2022`{=html} {#shih-et-al-2022-section}

**[`Conditional Imitation Learning for Multi-Agent Games`{=html}](https://arxiv.org/abs/2201.01448 "'Conditional Imitation Learning for Multi-Agent Games', Shih et al 2022"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Reinforcement Learning on Human Decision Models for Uniquely Collaborative AI Teammates”, Kantack 2021`{=html} {#kantack-2021-section}

**[`Reinforcement Learning on Human Decision Models for Uniquely Collaborative AI Teammates`{=html}](https://arxiv.org/abs/2111.09800 "'Reinforcement Learning on Human Decision Models for Uniquely Collaborative AI Teammates', Kantack 2021"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Scalable Online Planning via Reinforcement Learning Fine-Tuning”, Fickinger et al 2021`{=html} {#fickinger-et-al-2021-section}

**[`Scalable Online Planning via Reinforcement Learning Fine-Tuning`{=html}](https://arxiv.org/abs/2109.15316#facebook "'Scalable Online Planning via Reinforcement Learning Fine-Tuning', Fickinger et al 2021"){.link-annotated
.id-not .include-annotation link-icon="facebook" link-icon-type="svg"
link-icon-color="#1877f2"}**

## `“Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi”, Siu et al 2021`{=html} {#siu-et-al-2021-section}

**[`Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi`{=html}](https://arxiv.org/abs/2107.07630 "'Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi', Siu et al 2021"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings”, Hu et al 2021`{=html} {#hu-et-al-2021-4-section}

**[`Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings`{=html}](https://arxiv.org/abs/2106.09086#facebook "'Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings', Hu et al 2021"){.link-annotated
.id-not .include-annotation link-icon="facebook" link-icon-type="svg"
link-icon-color="#1877f2"}**

## `“On the Critical Role of Conventions in Adaptive Human-AI Collaboration”, Shih et al 2021`{=html} {#shih-et-al-2021-section}

**[`On the Critical Role of Conventions in Adaptive Human-AI Collaboration`{=html}](https://arxiv.org/abs/2104.02871 "'On the Critical Role of Conventions in Adaptive Human-AI Collaboration', Shih et al 2021"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Off-Belief Learning”, Hu et al 2021`{=html} {#hu-et-al-2021-5-section}

**[`Off-Belief Learning`{=html}](https://arxiv.org/abs/2103.04000#facebook "'Off-Belief Learning', Hu et al 2021"){.link-annotated
.id-not .include-annotation link-icon="facebook" link-icon-type="svg"
link-icon-color="#1877f2"}**

## `“Continuous Coordination As a Realistic Scenario for Lifelong Learning”, Nekoei et al 2021`{=html} {#nekoei-et-al-2021-section}

**[`Continuous Coordination As a Realistic Scenario for Lifelong Learning`{=html}](https://arxiv.org/abs/2103.03216 "'Continuous Coordination As a Realistic Scenario for Lifelong Learning', Nekoei et al 2021"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games”, Yu et al 2021`{=html} {#yu-et-al-2021-2-section}

**[`The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games`{=html}](https://arxiv.org/abs/2103.01955 "'The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games', Yu et al 2021"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Theory of Mind for Deep Reinforcement Learning in Hanabi”, Fuchs et al 2021`{=html} {#fuchs-et-al-2021-section}

**[`Theory of Mind for Deep Reinforcement Learning in Hanabi`{=html}](https://arxiv.org/abs/2101.09328 "'Theory of Mind for Deep Reinforcement Learning in Hanabi', Fuchs et al 2021"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Evaluating the Rainbow DQN Agent in Hanabi With Unseen Partners”, Canaan et al 2020`{=html} {#canaan-et-al-2020-2-section}

**[`Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners`{=html}](https://arxiv.org/abs/2004.13291 "'Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners', Canaan et al 2020"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“Generating and Adapting to Diverse Ad-Hoc Cooperation Agents in Hanabi”, Canaan et al 2020`{=html} {#canaan-et-al-2020-1-section}

**[`Generating and Adapting to Diverse Ad-Hoc Cooperation Agents in Hanabi`{=html}](https://arxiv.org/abs/2004.13710 "'Generating and Adapting to Diverse Ad-Hoc Cooperation Agents in Hanabi', Canaan et al 2020"){.link-annotated
.id-not .include-annotation link-icon="𝛘" link-icon-type="text"
link-icon-color="#b31b1b"}**

## `“"Other-Play" for Zero-Shot Coordination”, Hu et al 2020`{=html} {#hu-et-al-2020-section}

**[`"Other-Play" for Zero-Shot Coordination`{=html}](https://arxiv.org/abs/2003.02979#facebook "'"Other-Play" for Zero-Shot Coordination', Hu et al 2020"){.link-annotated
.id-not .include-annotation link-icon="facebook" link-icon-type="svg"
link-icon-color="#1877f2"}**

## `“Improving Policies via Search in Cooperative Partially Observable Games”, Lerer et al 2019`{=html} {#lerer-et-al-2019-section}

**[`Improving Policies via Search in Cooperative Partially Observable Games`{=html}](https://arxiv.org/abs/1912.02318#facebook "'Improving Policies via Search in Cooperative Partially Observable Games', Lerer et al 2019"){.link-annotated
.id-not .include-annotation link-icon="facebook" link-icon-type="svg"
link-icon-color="#1877f2"}**

## `“Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning”, Hu & Foerster 2019`{=html} {#hu-foerster-2019-section}

**[`Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning`{=html}](https://arxiv.org/abs/1912.02288#facebook "'Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning', Hu & Foerster 2019"){.link-annotated
.id-not .include-annotation link-icon="facebook" link-icon-type="svg"
link-icon-color="#1877f2"}**

## `“The Hanabi Challenge: A New Frontier for AI Research”, Bard et al 2019`{=html} {#bard-et-al-2019-section}

**[`The Hanabi Challenge: A New Frontier for AI Research`{=html}](https://arxiv.org/abs/1902.00506#deepmind "'The Hanabi Challenge: A New Frontier for AI Research', Bard et al 2019"){.link-annotated
.id-not .include-annotation link-icon="deepmind" link-icon-type="svg"
link-icon-color="#4185f4"}**

## `“Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning”, Foerster et al 2018`{=html} {#foerster-et-al-2018-section}

**[`Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning`{=html}](https://arxiv.org/abs/1811.01458#deepmind "'Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning', Foerster et al 2018"){.link-annotated
.id-not .include-annotation link-icon="deepmind" link-icon-type="svg"
link-icon-color="#4185f4"}**

## `“Playing <em>Hanabi</em> Near-Optimally”, Bouzy 2017`{=html} {#bouzy-2017-section}

**[`Playing <em>Hanabi</em> Near-Optimally`{=html}](/doc/reinforcement-learning/imperfect-information/hanabi/2017-bouzy.pdf "'Playing <em>Hanabi</em> Near-Optimally', Bouzy 2017"){.link-annotated
.id-not .include-annotation link-icon="pdf" link-icon-type="svg"
link-icon-color="#f40f02"}**

## `“How to Make the Perfect Fireworks Display: Two Strategies for <em>Hanabi</em>”, Cox et al 2015`{=html} {#cox-et-al-2015-section}

**[`How to Make the Perfect Fireworks Display: Two Strategies for <em>Hanabi</em>`{=html}](/doc/reinforcement-learning/imperfect-information/hanabi/2015-cox.pdf "'How to Make the Perfect Fireworks Display: Two Strategies for <em>Hanabi</em>', Cox et al 2015"){.link-annotated
.id-not .include-annotation link-icon="pdf" link-icon-type="svg"
link-icon-color="#f40f02"}**

## `“State-Of-The-Art Hanabi Bots + Simulation Framework in Rust”`{=html} {#__eOZcGAC-section}

**[`State-of-the-art Hanabi bots + simulation framework in rust`{=html}](https://github.com/WuTheFWasThat/hanabi.rs "State-of-the-art Hanabi bots + simulation framework in rust"){.id-not
.include-annotation link-icon="github" link-icon-type="svg"}**

## Sort By Magic

::: {demo-type="sort-by-magic-preface"}
Annotations sorted by machine learning into [inferred \'tags\'](/design#future-tag-features){#gwern-design--future-tag-features
.link-annotated-partial}. This provides an alternative way to browse: instead of by *date* order, one can browse in *topic* order. The \'sorted\' list has been automatically clustered into multiple sections & auto-labeled for easier browsing.

Beginning with the newest annotation, it uses the embedding of each annotation to attempt to create a list of nearest-neighbor annotations, creating a progression of topics. For more details, see the link.
:::

### `multi-agent-rl` {.collapse title="Machine-generated tag name for the following cluster of links."}

[\[see previous entry\]](#nekoei-et-al-2021-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#rutherford-et-al-2023-section){.include
.include-even-when-collapsed}

### `multi-agent-cooperation` {.collapse title="Machine-generated tag name for the following cluster of links."}

[\[see previous entry\]](#grooten-et-al-2022-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#yu-et-al-2021-2-section){.include
.include-even-when-collapsed}

### `online-planning` {.collapse title="Machine-generated tag name for the following cluster of links."}

[\[see previous entry\]](#hu-foerster-2019-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#foerster-et-al-2018-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#hu-et-al-2021-5-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#hu-et-al-2021-4-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#fickinger-et-al-2021-section){.include
.include-even-when-collapsed}

### `hanabi-cooperation` {.collapse title="Machine-generated tag name for the following cluster of links."}

[\[see previous entry\]](#cox-et-al-2015-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#bouzy-2017-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#lerer-et-al-2019-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#hu-et-al-2022-2-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#kantack-2021-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#siu-et-al-2021-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#bard-et-al-2019-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#fuchs-et-al-2021-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#canaan-et-al-2020-2-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#canaan-et-al-2020-1-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#zand-et-al-2022-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#hu-et-al-2020-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#lucas-allen-2022-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#shih-et-al-2021-section){.include
.include-even-when-collapsed}

[\[see previous entry\]](#shih-et-al-2022-section){.include
.include-even-when-collapsed}

## Wikipedia (1) {#titled-links-wikipedia .collapse}

1.  **[`Hanabi (card game)`{=html}](https://en.wikipedia.org/wiki/Hanabi_(card_game) "Hanabi (card game)"){.link-annotated-partial
    .id-not .include-annotation link-icon="wikipedia"
    link-icon-type="svg"}**

# Bibliography {#link-bibliography-section}

1.  `https://arxiv.org/abs/2311.10090`:
    [`“JaxMARL: Multi-Agent RL Environments in JAX”`{=html}](https://arxiv.org/abs/2311.10090 "'JaxMARL: Multi-Agent RL Environments in JAX', Rutherford et al 2023"){#rutherford-et-al-2023
    .link-annotated},
    [[Alexander Rutherford](https://en.wikipedia.org/wiki/Alexander_Rutherford "Alexander Rutherford"){.id-not}, Benjamin Ellis, Matteo Gallici[, [Jonathan Cook](https://en.wikipedia.org/wiki/Jonathan_Cook "Jonathan Cook"){.id-not}, Andrei Lupu, Gardar Ingvarsson, Timon Willi, Akbir Khan, Christian Schroeder de Witt, Alexandra Souly, Saptarashmi Bandyopadhyay, Mikayel Samvelyan, Minqi Jiang, Robert Tjarko Lange, Shimon Whiteson, Bruno Lacerda, Nick Hawes, Tim Rocktaschel, [Chris Lu](https://en.wikipedia.org/wiki/Chris_Lu "Chris Lu"){.id-not}, Jakob Nicolaus Foerster]{.collapse}]{.author}

    [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Farxiv.org%252Fabs%252F2311.10090.html "Directory-tag link-bibliography for link https://arxiv.org/abs/2311.10090"){.id-not
    .include-even-when-collapsed}]{.collapse
    .tag-index-link-bibliography-block}

2.  `https://arxiv.org/abs/2103.01955`:
    [`“The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games”`{=html}](https://arxiv.org/abs/2103.01955 "'The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games', Yu et al 2021"){#yu-et-al-2021-2
    .link-annotated},
    [Chao Yu, Akash Velu, Eugene Vinitsky[, Yu Wang, Alexandre Bayen, [Yi Wu](https://en.wikipedia.org/wiki/Yi_Wu "Yi Wu"){.id-not}]{.collapse}]{.author}

    [[link-bibliography](/metadata/annotation/link-bibliography/https%253A%252F%252Farxiv.org%252Fabs%252F2103.01955.html "Directory-tag link-bibliography for link https://arxiv.org/abs/2103.01955"){.id-not
    .include-even-when-collapsed}]{.collapse
    .tag-index-link-bibliography-block}