[2006.05990] What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study

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

[2006.05990] What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study 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:2006.05990 (cs) [Submitted on 10 Jun 2020] Title: What Matters In On-Policy Reinforcement Learning? A Large-Scale Empirical Study Authors: Marcin Andrychowicz , Anton Raichuk , Piotr Stańczyk , Manu Orsini , Sertan Girgin , Raphael Marinier , Léonard Hussenot , Matthieu Geist , Olivier Pietquin , Marcin Michalski , Sylva

related reading

• On-Policy Distillation - Thinking Machines Labthinkingmachines.ai
• [1709.06560] Deep Reinforcement Learning that Mattersarxiv.org
• The 37 Implementation Details of Proximal Policy Optimization · The ICLR Blog Trackiclr-blog-track.github.io
• Q-learning is not yet scalableseohong.me
• Key Papers in Deep RL - Spinning Up documentationspinningup.openai.com
• Part 1: Key Concepts in RL - Spinning Up documentationspinningup.openai.com
• Debugging Reinforcement Learning Systemsandyljones.com
• A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
• State of RL for reasoning LLMs | A. Weersaweers.de
• Reinforcement learning - Wikipediaen.wikipedia.org
• Selected Publicationsjoschu.net
• pistar06.pdfpi.website