部分観測下における同変強化学習
Equivariant Reinforcement Learning under Partial Observability
部分観測環境で群対称性の同変性をニューラルネットに組み込み、過去の解を再利用することでサンプル効率と性能を高める強化学習手法を提案した。
著者: Hai Nguyen, Andrea Baisero, David Klee, Dian Wang, Robert Platt, Christopher Amato
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
Incorporating inductive biases is a promising approach for tackling challenging robot learning domains with sample-efficient solutions. This paper identifies partially observable domains where symmetries can be a useful inductive bias for efficient learning. Specifically, by encoding the equivariance regarding specific group symmetries into the neural networks, our actor-critic reinforcement learning agents can reuse solutions in the past for related scenarios. Consequently, our equivariant agents outperform non-equivariant approaches significantly in terms of sample efficiency and final performance, demonstrated through experiments on a range of robotic tasks in simulation and real hardware.
