SIMA 2：一个与你在虚拟3D世界中一起玩耍、推理和学习的智能体。

SIMA 2：一个与你在虚拟3D世界中一起玩耍、推理和学习的智能体。
SIMA 2: An agent that plays, reasons, and learns with you in virtual 3D worlds

原始链接: https://deepmind.google/blog/sima-2-an-agent-that-plays-reasons-and-learns-with-you-in-virtual-3d-worlds/

这项研究是SIMA 2团队的大规模协作成果，该团队由50多名研究人员组成，并感谢谷歌和谷歌DeepMind领导的大力支持。该项目受益于过往团队成员、游戏开发者（包括《Valheim》、《No Man’s Sky》和《Teardown》的开发者）以及专注于模型开发（Genie 3）和关键项目组件的合作伙伴团队的贡献。许多谷歌内部团队——包括法律、营销和安全部门——也提供了重要帮助。这项工作献给已故的同事菲利克斯·希尔和法比奥·帕尔多，以表彰他们对该领域的持久影响。致谢强调了这项研究工作的真正跨学科和协作性质。

DeepMind 发布了 SIMA 2，一种能够在虚拟 3D 世界中游戏、推理和学习的 AI 智能体。该智能体利用试错学习，结合来自 Google 的 Gemini 模型的反馈，来完成日益复杂的任务。值得注意的是，SIMA 2 可以利用自身的经验来训练后续更强大的版本——这是朝着创造能够适应不同环境的通用 AI 智能体迈出的重要一步。初步观察表明，该智能体即使在新生成的世界（“Genie 环境”）中也能展现自我改进。然而，一位 Hacker News 用户指出演示视频中的文本输出可能存在不一致之处，引发了对标注真实性的质疑，以及 Google 是否夸大了智能体的能力。SIMA 2 与 Gemini 之间的关系也在讨论中，有猜测认为 SIMA 2 是*基于* Gemini 模型构建的智能体。

原文

This research was developed by the SIMA 2 team: Maria Abi Raad, John Agapiou, Frederic Besse, Andrew Bolt, Sarah Chakera, Harris Chan, Jeff Clune, Alexandra Cordell, Martin Engelcke, Ryan Faulkner, Maxime Gazeau, Arne Olav Hallingstad, Tim Harley, Ed Hirst, Drew Hudson, Laura Kampis, Sheleem Kashem, Thomas Keck, Matija Kecman, Oscar Knagg, Alexander Lerchner, Bonnie Li, Yulan Liu, Cong Lu, Maria Loks-Thompson, Joseph Marino, Kay McKinney, Piermaria Mendolicchio, Anna Mitenkova, Alexandre Moufarek, Fabio Pardo, Ollie Purkiss, David Reichert, John Reid, Tyson Roberts, Daniel P. Sawyer, Tim Scholtes, Daniel Slater, Hubert Soyer, Kaustubh Sridhar, Peter Stys, Tayfun Terzi, Davide Vercelli, Bojan Vujatovic, Jane X. Wang, Luyu Wang, Duncan Williams, and Lei M. Zhang.

For their leadership, guidance, and support, we thank: Satinder Singh Baveja, Adrian Bolton, Zoubin Ghahramani, Raia Hadsell, Demis Hassabis, Shane Legg, Volodymyr Mnih, and Daan Wierstra.

With much gratitude to partial contributors and past members: Alex Cullum, Karol Gregor, Rosemary Ke, Junkyung Kim, Matthew Jackson, Andrew Lampinen, Loic Matthey, Hannah Openshaw, and Zhengdong Wang.

Special thanks to all of the game developers who partnered with us: Coffee Stain (Valheim, Satisfactory, Goat Simulator 3), Foulball Hangover (Hydroneer), Hello Games (No Man's Sky), Keen Software House (Space Engineers), RubberbandGames (Wobbly Life), Strange Loop Games (Eco), Thunderful Games (ASKA, The Gunk, Road 96, Steamworld Build), and Tuxedo Labs & Saber Interactive (Teardown).

We thank Vika Koriakin, Duncan Smith, Nilesh Ray, Matt Miller, Leen Verburgh, Ashyana Kachra, Phil Esposito, Dimple Vijaykumar, Piers Wingfield, Lucie Kerley for their invaluable partnership in developing and refining key components of this project.

We also thank Jack Parker-Holder, Shlomi Fruchter, and the rest of the Genie team for access to the Genie 3 model.

We’d like to recognize the many teams across Google and Google DeepMind that have contributed to this effort including Legal, Marketing, Communications, Responsibility and Safety Council, Responsible Development and Innovation, Policy, Strategy and Operations, and our Business and Corporate Development teams. We'd also like to thank all GDM teams that are not explicitly mentioned here for their continued support.

Finally, we dedicate this work to the memory of our colleagues Felix Hill and Fabio Pardo, whose contributions to our field continue to inspire us.

SIMA 2：一个与你在虚拟3D世界中一起玩耍、推理和学习的智能体。 SIMA 2: An agent that plays, reasons, and learns with you in virtual 3D worlds

SIMA 2：一个与你在虚拟3D世界中一起玩耍、推理和学习的智能体。
SIMA 2: An agent that plays, reasons, and learns with you in virtual 3D worlds