[2312.12568] Scaling Opponent Shaping to High Dimensional Games

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. arXiv Operational Status Get status notifications via email or slack

[2312.12568] Scaling Opponent Shaping to High Dimensional Games Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Artificial Intelligence arXiv:2312.12568 (cs) [Submitted on 19 Dec 2023 ( v1 ), last revised 10 Feb 2024 (this version, v3)] Title: Scaling Opponent Shaping to High Dimensional Games Authors: Akbir Khan , Timon Willi , Newton Kwan , Andrea Tacchetti , Chris Lu , Edward Grefenstette , Tim Rocktäschel , Jakob Foerster View a PDF of the paper titled Scaling Opponent Shaping

related reading

• It Looks Like You’re Trying To Take Over The World · Gwern.net (reader mode)gwern.net
• Game theory as an engine for large-scale data analysis — Google DeepMinddeepmind.com
• Game theory as an engine for large-scale data analysis — Google DeepMinddeepmind.google
• Q-learning is not yet scalableseohong.me
• [AN #70]: Agents that help humans who are still learning about their own preferences — LessWronglesswrong.com
• Towards a scale-free theory of intelligent agencymindthefuture.info
• Natural Deception with RL - Rajan Agarwalrajan.sh
• How DeepMind's Generally Capable Agents Were Trained — LessWronglesswrong.com
• VGC-Bench: Towards Mastering Diverse Team Strategies in Competitive Pokémonarxiv.org
• Consensus Multiplicative Weights Update: Learningto Learn using Projector-based Game Signaturesarxiv.org
• Towards a scale-free theory of intelligent agency — AI Alignment Forumalignmentforum.org
• EdgeBench | Scaling Laws of Environment Learningedge-bench.org