Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
This addresses the challenge of efficient policy transfer across multiple robots in robotics, which is incremental as it builds on existing one-to-one transfer methods.
The paper tackles the problem of transferring an expert policy from a source robot to multiple different robots, achieving up to 3.2× efficiency improvement for manipulation policy transfer and 2.4× for locomotion policy transfer compared to baseline methods.
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 approach to determine an optimized robot evolution tree. Experiments have shown that our method is able to improve the efficiency of one-to-three transfer of manipulation policy by up to 3.2$\times$ and one-to-six transfer of agile locomotion policy by 2.4$\times$ in terms of simulation cost over the baseline of launching multiple independent one-to-one policy transfers.