[2404.06356] Policy-Guided Diffusion

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

[2404.06356] Policy-Guided Diffusion Skip to main content arXiv is now an independent nonprofit! Learn more × Search arXiv Press Enter to search · Advanced search --> Computer Science > Machine Learning arXiv:2404.06356 (cs) [Submitted on 9 Apr 2024] Title: Policy-Guided Diffusion Authors: Matthew Thomas Jackson , Michael Tryfan Matthews , Cong Lu , Benjamin Ellis , Shimon Whiteson , Jakob Foerster View a PDF of the paper titled Policy-Guided Diffusion, by Matthew Thomas Jackson and 5 other authors View PDF HTML (experimental) Abstract: In many real-world settings, agents must lea

related reading

• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• [2404.19756] KAN: Kolmogorov-Arnold Networksarxiv.org
• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• Universal Guidance for Diffusion Modelsarxiv.org
• [2406.04219] Multi-Agent Imitation Learning: Value is Easy, Regret is Hardarxiv.org
• [2503.11615v2] From Score Matching to Diffusion: A Fine-Grained Error Analysis in the Gaussian Settingarxiv.org
• [1707.06347] Proximal Policy Optimization Algorithmsarxiv.org
• [2401.05654] Towards Conversational Diagnostic AIarxiv.org
• [2604.00626] A Survey of On-Policy Distillation for Large Language Modelsarxiv.org
• [2404.01413v2] Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Dataarxiv.org
• [2006.05990] What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Studyarxiv.org
• [2506.03719] On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticityarxiv.org