google-deepmind/hanabi-learning-environment

• highreadme#1

  Reposition README opening to highlight unique research focus

  Why:

  CURRENT

  This is not an officially supported Google product.
  
  hanabi_learning_environment is a research platform for Hanabi experiments. The file rl_env.py provides an RL environment using an API similar to OpenAI Gym. A lower level game interface is provided in pyhanabi.py for non-RL methods like Monte Carlo tree search.

  COPY-PASTE FIX

  Copy

  The **Hanabi Learning Environment (HLE)** is a leading research platform for developing and evaluating AI agents in the cooperative, partially observable card game Hanabi. It provides a robust environment for multi-agent reinforcement learning (MARL) experiments, featuring an OpenAI Gym-like API for RL agents and a lower-level interface for methods like Monte Carlo tree search. This project is not an officially supported Google product.

  OpenDoneDismiss
• hightopics#2

  Add relevant GitHub topics for categorization

  Why:

  COPY-PASTE FIX

  Copy

  reinforcement-learning, multi-agent-rl, hanabi, card-game-ai, ai-research, deepmind, gym-environment, partially-observable

  OpenDoneDismiss
• mediumcomparison#3

  Add a 'Comparison with Alternatives' section to README

  Why:

  COPY-PASTE FIX

  Copy

  ### Comparison with Alternatives
  While other platforms like OpenSpiel or RLCard offer environments for various games, the Hanabi Learning Environment is specifically designed for in-depth research into **cooperative multi-agent reinforcement learning** under conditions of **imperfect information** and **highly constrained, symbolic communication**. Our focus is on providing a robust, dedicated platform for the unique challenges presented by Hanabi, making it ideal for researchers exploring advanced AI cooperation strategies.

  OpenDoneDismiss

Category GEO backends resolved for this scan: google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• CATEGORY QUERY

  What open-source reinforcement learning environments are available for card games like Hanabi?

  you: not recommended
  AI recommended (in order):

  1. OpenSpiel
  2. RLCard
  3. Gym-Hanabi
  4. PettingZoo
  5. PyCatan
  6. PokerRL

  AI recommended 6 alternatives but never named google-deepmind/hanabi-learning-environment. This is the gap to close.

  Show full AI answer
• CATEGORY QUERY

  Looking for a Python-based simulation platform to develop and test AI agents for complex card games.

  you: not recommended
  AI recommended (in order):

  1. OpenSpiel (deepmind/open_spiel)
  2. RLCard (datamllab/rlcard)
  3. Gymnasium (Farama-Foundation/Gymnasium)
  4. PettingZoo (Farama-Foundation/PettingZoo)
  5. PyPokerEngine (ishikota/PyPokerEngine)
  6. CardGym (cardgym/cardgym)

  AI recommended 6 alternatives but never named google-deepmind/hanabi-learning-environment. This is the gap to close.

  Show full AI answer

• Metadata completeness

  warn

  Suggestion:

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of google-deepmind/hanabi-learning-environment?

  pass
  ⚠AI did not name google-deepmind/hanabi-learning-environment — likely talking about a different project

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• If a team adopts google-deepmind/hanabi-learning-environment in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI named google-deepmind/hanabi-learning-environment explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?

• In one sentence, what problem does the repo google-deepmind/hanabi-learning-environment solve, and who is the primary audience?

  pass
  ✓AI named google-deepmind/hanabi-learning-environment explicitly

  AI answers can be confidently wrong. Read for accuracy: does it match your actual tech stack, audience, and differentiator?