Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL

This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions.

Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL Overcoming the Sim-to-Real Gap: Leveraging Simulation to Learn to Explore for Real-World RL Andrew Wagenmaker 1 Kevin Huang 2 Liyiming Ke 2 Byron Boots 2 Kevin Jamieson 2 Abhishek Gupta 2 ( 1 University of California, Berkeley 2 University of Washington ajwagen@berkeley.edu, {kehuang,kayke,bboots,jamieson,abhgupta}@cs.washington.edu ) Abstract In order to mitigate the sample complexity of real-world reinforcement learning, common practice is to first train a policy in a simulator where samples are cheap

related reading

• State of Robot Learning, December 2025vedder.io
• Domain Randomization for Sim2Real Transfer | Lil'Loglilianweng.github.io
• A (Long) Peek into Reinforcement Learning | Lil'Loglilianweng.github.io
• Exploration for the Efficient Deployment of Reinforcement Learning Agentsopenreview.net
• Reinforcement Learning via Implicit Imitation Guidancearxiv.org
• Eric Jang: Robots Must Be Ephemeralizedblog.evjang.com
• Imitation Bootstrapped Reinforcement Learningarxiv.org
• [2307.04354] Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Dataar5iv.labs.arxiv.org
• pistar06.pdfpi.website
• Learning dexterity | OpenAIopenai.com
• [2211.05311] When is Realizability Sufficient for Off-Policy Reinforcement Learning?ar5iv.labs.arxiv.org
• Should I Use Offline RL or Imitation Learning? – The Berkeley Artificial Intelligence Research Blogbair.berkeley.edu