arXiv 2610.20584 · cs.CV · 2026-10-14
Player-1: Learning to Play from Synthetic Experience
Mingyu Ouyang, Yiran Wang, Siyuan Hu, Xingyilang Yin, Huiqiang Sun, Guangzhi Wang, Junfu Pu, Cheng Cheng 等 12 人
ARC Lab, Tencent
在最新榜 #6 2026-W42 第 5 名 本站收录于 2026-10-21
一句话要点
Player-1 用合成交互经验做后训练，让电脑操作型 Agent 学会玩游戏。
Player-1 post-trains computer-use agents on synthetic experience so they learn to control games beyond demonstrations.
阅读 arXiv 原文 PDF Hugging Face 讨论 代码仓库 项目页
主题与学科
同主题：智能体
- Raven: The Harness of Harnesses for Composable Agentic Intelligence ▲748
- False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents ▲642
- BizAgentBench: Unveiling Hidden Challenges in Deploying Long-Horizon Agents for Real-World Business ▲490
- Omni-IO Skills: Harnessing Your Agent Omni-Native ▲485
- OpenGCUA: Toward a Fully Open Stack for Generalist Computer Use ▲330
数据说明
元数据来自 arXiv API（已核实）；点赞来自 Hugging Face 每日论文；引用来自 Semantic Scholar。最近刷新 2026-10-22。
要点由本站根据摘要自写，不转载摘要原文，请阅读原文。