Predicting Sim-to-Real Transfer with Probabilistic Dynamics Models
This addresses the challenge of selecting training setups and policies in simulation without extensive real-world testing, primarily for robotics researchers and practitioners.
The paper tackles the problem of predicting sim-to-real transfer performance for RL policies, proposing a transfer metric that correlates highly with policy performance in both simulated and real-world robotic manipulation tasks.
We propose a method to predict the sim-to-real transfer performance of RL policies. Our transfer metric simplifies the selection of training setups (such as algorithm, hyperparameters, randomizations) and policies in simulation, without the need for extensive and time-consuming real-world rollouts. A probabilistic dynamics model is trained alongside the policy and evaluated on a fixed set of real-world trajectories to obtain the transfer metric. Experiments show that the transfer metric is highly correlated with policy performance in both simulated and real-world robotic environments for complex manipulation tasks. We further show that the transfer metric can predict the effect of training setups on policy transfer performance.