[2404.02688] Reinforcement Learning in Categorical Cybernetics

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

[2404.02688] Reinforcement Learning in Categorical Cybernetics 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:2404.02688 (cs) [Submitted on 3 Apr 2024 ( v1 ), last revised 24 Sep 2025 (this version, v2)] Title: Reinforcement Learning in Categorical Cybernetics Authors: Jules Hedges (University of Strathclyde), Riu Rodríguez Sakamoto (University of Strathclyde) View a PDF of the paper titled Reinforcement Learning in Categorical Cybernetics, by Jules Hedges (

related reading

• [2401.05566] Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Trainingarxiv.org
• Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Reviewarxiv.org
• [2404.19756] KAN: Kolmogorov-Arnold Networksarxiv.org
• [2301.08028] A Tutorial on Meta-Reinforcement Learningarxiv.org
• [2402.14740] Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMsarxiv.org
• [2406.11717] Refusal in Language Models Is Mediated by a Single Directionarxiv.org
• [2406.04219] Multi-Agent Imitation Learning: Value is Easy, Regret is Hardarxiv.org
• [2309.00267] RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedbackarxiv.org
• [2605.12474] Reward Hacking in Rubric-Based Reinforcement Learningarxiv.org
• [2402.12875] Chain of Thought Empowers Transformers to Solve Inherently Serial Problemsarxiv.org
• [2406.17583] Towards Compositional Interpretability for XAIarxiv.org
• [2006.05990] What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Studyarxiv.org