形態を越えた転移のための階層的分離模倣
Hierarchically Decoupled Imitation for Morphological Transfer
低レベル方策を単純な形態のエージェントから模倣させ、KL正則化で高レベル方策を安定学習させることで、複雑な形態のエージェントへの長距離タスクの転移効率を向上させた研究。
著者: Donald J. Hejna, Pieter Abbeel, Lerrel Pinto
分類: cs.LG, cs.AI, cs.RO, stat.ML
原文アブストラクト
Learning long-range behaviors on complex high-dimensional agents is a fundamental problem in robot learning. For such tasks, we argue that transferring learned information from a morphologically simpler agent can massively improve the sample efficiency of a more complex one. To this end, we propose a hierarchical decoupling of policies into two parts: an independently learned low-level policy and a transferable high-level policy. To remedy poor transfer performance due to mismatch in morphologies, we contribute two key ideas. First, we show that incentivizing a complex agent's low-level to imitate a simpler agent's low-level significantly improves zero-shot high-level transfer. Second, we show that KL-regularized training of the high level stabilizes learning and prevents mode-collapse. Finally, on a suite of publicly released navigation and manipulation environments, we demonstrate the applicability of hierarchical transfer on long-range tasks across morphologies. Our code and videos can be found at https://sites.google.com/berkeley.edu/morphology-transfer.
