Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control
It addresses sim-to-real transfer for robotic manipulation, an incremental improvement in curriculum learning methods.
The paper tackles sparse reward reinforcement learning by adaptively generating task difficulty from demonstrations, improving sim-to-real transfer for visuomotor control. It demonstrates zero-shot transfer on pick-and-stow and block stacking tasks.
We propose Adaptive Curriculum Generation from Demonstrations (ACGD) for reinforcement learning in the presence of sparse rewards. Rather than designing shaped reward functions, ACGD adaptively sets the appropriate task difficulty for the learner by controlling where to sample from the demonstration trajectories and which set of simulation parameters to use. We show that training vision-based control policies in simulation while gradually increasing the difficulty of the task via ACGD improves the policy transfer to the real world. The degree of domain randomization is also gradually increased through the task difficulty. We demonstrate zero-shot transfer for two real-world manipulation tasks: pick-and-stow and block stacking. A video showing the results can be found at https://lmb.informatik.uni-freiburg.de/projects/curriculum/