---
format: "aidr-story-markdown/v1"
id: "517f3f67952a2bbf5610a131cc8e6e10b4ce2754f555727cfb5c9ca3b068b68e"
canonical_url: "https://aidr.today/517f3f67?lang=en"
title: "Player-1: Learning to Play from Synthetic Experience"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-15T00:00:00.000Z"
category: "Frameworks"
topics: ["agent","framework"]
source_urls: ["https://huggingface.co/papers/2610.20584"]
summary: "Player-1 is a post-training framework for learning game control through synthetic experience. The framework fine-tunes computer-use models on 6,044 curated gameplay trajectories and utilizes Player-1-Gym, a collection of sixteen synthetic 2D and 3D environments, to support multi-environment reinforcement learning."
---

# Player\-1: Learning to Play from Synthetic Experience

> [Open the canonical story](<https://aidr.today/517f3f67?lang=en>)

**Published:** 2026-10-15T00:00:00.000Z
**Category:** Frameworks
**Topics:** agent, framework

## Summary

Player\-1 is a post\-training framework for learning game control through synthetic experience\. The framework fine\-tunes computer\-use models on 6,044 curated gameplay trajectories and utilizes Player\-1\-Gym, a collection of sixteen synthetic 2D and 3D environments, to support multi\-environment reinforcement learning\.

## Sources

- [Story source](<https://huggingface.co/papers/2610.20584>)