構造化直交行列によるコンパクト方策のスケーラブルな進化最適化
Structured Evolution with Compact Architectures for Scalable Policy Optimization
構造化ランダム直交行列を用いた勾配近似によるブラックボックス最適化手法を提案し、少ないパラメータでロボティクス課題を効率的に解けるコンパクト方策を学習できることを示した。
著者: Krzysztof Choromanski, Mark Rowland, Vikas Sindhwani, Richard E. Turner, Adrian Weller
分類: cs.LG, cs.RO, stat.ML
原文アブストラクト
We present a new method of blackbox optimization via gradient approximation with the use of structured random orthogonal matrices, providing more accurate estimators than baselines and with provable theoretical guarantees. We show that this algorithm can be successfully applied to learn better quality compact policies than those using standard gradient estimation techniques. The compact policies we learn have several advantages over unstructured ones, including faster training algorithms and faster inference. These benefits are important when the policy is deployed on real hardware with limited resources. Further, compact policies provide more scalable architectures for derivative-free optimization (DFO) in high-dimensional spaces. We show that most robotics tasks from the OpenAI Gym can be solved using neural networks with less than 300 parameters, with almost linear time complexity of the inference phase, with up to 13x fewer parameters relative to the Evolution Strategies (ES) algorithm introduced by Salimans et al. (2017). We do not need heuristics such as fitness shaping to learn good quality policies, resulting in a simple and theoretically motivated training mechanism.
