Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer

arXiv:2405.03534v1 Announce Type: cross
Abstract: We investigate the problem of transferring an expert policy from a source robot to multiple different robots. To solve this problem, we propose a method named $Meta$-$Evolve$ that uses continuous robot evolution to efficiently transfer the policy to each target robot through a set of tree-structured evolutionary robot sequences. The robot evolution tree allows the robot evolution paths to be shared, so our approach can significantly outperform naive one-to-one policy transfer. We present a heuristic …

abstract arxiv continuous cs.ai cs.lg cs.ne cs.ro evolution expert meta multiple policy robot robots set solve through transfer tree type