Simulation-Aided Policy Tuning for Black-Box Robot Learning

Abstract

How can robots learn and adapt to new tasks and situations with little data? Systematic exploration and simulation are crucial tools for efficient robot learning. We present a novel black-box policy search algorithm focused on data-efficient policy improvements. The algorithm learns directly on the robot and treats simulation as an additional information source to speed up the learning process. At the core of the algorithm, a probabilistic model learns the dependence of the policy parameters and the robot learning objective not only by performing experiments on the robot, but also by leveraging data from a simulator. This substantially reduces interaction time with the robot. Using this model, we can guarantee improvements with high probability for each policy update, thereby facilitating fast, goal-oriented learning. We evaluate our algorithm on simulated fine-tuning tasks and demonstrate the data-efficiency of the proposed dual-information source optimization algorithm. In a real robot learning experiment, we show fast and successful task learning on a robot manipulator with the aid of an imperfect simulator.

References in corpus (8)

• Learning Quadrupedal Locomotion over Challenging Terrain
• Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
• How to Train Your Robot with Deep Reinforcement Learning; Lessons We've Learned
• Safe Controller Optimization for Quadrotors with Gaussian Processes
• Virtual vs. Real: Trading Off Simulations and Physical Experiments in Reinforcement Learning with Bayesian Optimization
• Automatic LQR Tuning Based on Gaussian Process Global Optimization
• Local policy search with Bayesian optimization
• Cautious Bayesian Optimization for Efficient and Scalable Policy Search