How To Pick The Domain Randomization Parameters For Sim-to-real Transfer Of Reinforcement Learning Policies?

Abstract

Recently, reinforcement learning (RL) algorithms have demonstrated remarkable success in learning complicated behaviors from minimally processed input. However, most of this success is limited to simulation. While there are promising successes in applying RL algorithms directly on real systems, their performance on more complex systems remains bottle-necked by the relative data inefficiency of RL algorithms. Domain randomization is a promising direction of research that has demonstrated impressive results using RL algorithms to control real robots. At a high level, domain randomization works by training a policy on a distribution of environmental conditions in simulation. If the environments are diverse enough, then the policy trained on this distribution will plausibly generalize to the real world. A human-specified design choice in domain randomization is the form and parameters of the distribution of simulated environments. It is unclear how to the best pick the form and parameters

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyvuong2019how

Related papers

• Understanding Domain Randomization For Sim-to-real Transfer (2021)0.00
• Data-efficient Domain Randomization With Bayesian Optimization (2020)13.28
• Post-convergence Sim-to-real Policy Transfer: A Principled Alternative To Cherry-picking (2025)0.00
• Robust Visual Domain Randomization For Reinforcement Learning (2019)0.00
• Statistical Guarantees For Offline Domain Randomization (2025)0.00
• Generating Automatic Curricula Via Self-supervised Active Domain Randomization (2020)0.00
• Robust Domain Randomised Reinforcement Learning Through Peer-to-peer Distillation (2020)0.00
• Overcoming The Sim-to-real Gap: Leveraging Simulation To Learn To Explore For Real-world RL (2024)5.84