Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
Deutsches Forschungszentrum für Künstliche Intelligenz (DFKI), 67663, Kaiserslautern, Germany
2
0
2
10
Fine-tuning policies transferred between different robots slashes training time for peg-in-hole tasks, outperforming both zero-shot transfer and training from scratch.
Robots can now learn to reliably assemble parts despite uncertainty, thanks to a reinforcement learning approach that breaks down the task into reusable skills.