AI News HubLIVE
原文

Self-Play Reinforcement Learning under Imperfect Information in Big 2

This paper studies self-play reinforcement learning in the four-player imperfect-information card game Big 2. PPO outperforms Monte Carlo Q approximation, SARSA, and Q-learning against various opponents. Moderate entropy regularization improves PPO by preventing overdeterministic policies, and current-policy self-play provides a stronger finite-budget curriculum than alternatives.

Article intelligence

EngineersAdvanced

Key points

  • Self-play RL framework developed for Big 2, a four-player imperfect-information game.
  • PPO consistently outperforms value-approximating methods across opponent types.
  • Entropy regularization and current-policy self-play are key to PPO's success.
  • Big 2 serves as a controlled benchmark for studying imperfect information, multiplayer interaction, delayed rewards, and variable action sets.

Why it matters

This matters because self-play RL framework developed for Big 2, a four-player imperfect-information game.

Technical impact

May affect agent architecture, tool calling, workflow automation, and product integration.

[2605.28863] Self-Play Reinforcement Learning under Imperfect Information in Big 2

[Submitted on 21 May 2026]

Title:Self-Play Reinforcement Learning under Imperfect Information in Big 2

View a PDF of the paper titled Self-Play Reinforcement Learning under Imperfect Information in Big 2, by Aalok Patwa

View PDF HTML (experimental)

Abstract:Imperfect-information multiplayer games test whether agents can act under hidden information, sparse rewards, and non-stationary opponents. We study these challenges in Big 2, a four-player imperfect-information card game. We develop a self-play RL framework for Big 2 that enables controlled comparisons between policy-gradient and value-approximating agents. Under a common environment, input representation, training budget, and evaluation protocol, PPO outperforms Monte Carlo Q approximation, SARSA, and Q-learning against random, greedy, and heuristic Big 2 opponents. We further find that moderate entropy regularization improves PPO by preventing the policy from becoming overly deterministic, and that current-policy self-play provides a stronger finite-budget curriculum than checkpoint self-play or fixed-opponent training. Together, these results show that Big 2 is a useful controlled setting for studying deep RL under imperfect information, multiplayer interaction, delayed rewards, and variable action sets.

Comments: 11 pages

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2605.28863 [cs.LG]

(or arXiv:2605.28863v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2605.28863

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Aalok Patwa [view email] [v1] Thu, 21 May 2026 21:56:09 UTC (1,115 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Self-Play Reinforcement Learning under Imperfect Information in Big 2, by Aalok Patwa

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-05

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)