Data-efficient Domain Randomization With Bayesian Optimization

Abstract

When learning policies for robot control, the required real-world data is typically prohibitively expensive to acquire, so learning in simulation is a popular strategy. Unfortunately, such polices are often not transferable to the real world due to a mismatch between the simulation and reality, called 'reality gap'. Domain randomization methods tackle this problem by randomizing the physics simulator (source domain) during training according to a distribution over domain parameters in order to obtain more robust policies that are able to overcome the reality gap. Most domain randomization approaches sample the domain parameters from a fixed distribution. This solution is suboptimal in the context of sim-to-real transferability, since it yields policies that have been trained without explicitly optimizing for the reward on the real system (target domain). Additionally, a fixed distribution assumes there is prior knowledge about the uncertainty over the domain parameters. In this paper,

Stats

• citations58
• S2 citations—
• github stars0
• HF likes0
• heat score13.28
• arxiv keymuratore2020data

Related papers

• Understanding Domain Randomization For Sim-to-real Transfer (2021)0.00
• How To Pick The Domain Randomization Parameters For Sim-to-real Transfer Of Reinforcement Learning Policies? (2019)0.00
• Statistical Guarantees For Offline Domain Randomization (2025)0.00
• Robust Visual Domain Randomization For Reinforcement Learning (2019)0.00
• Post-convergence Sim-to-real Policy Transfer: A Principled Alternative To Cherry-picking (2025)0.00
• Alternating Optimisation And Quadrature For Robust Control (2016)7.16
• Robust Adversarial Policy Optimization Under Dynamics Uncertainty (2026)0.00
• Overcoming The Sim-to-real Gap: Leveraging Simulation To Learn To Explore For Real-world RL (2024)5.84