モデルフリー強化学習のための二次ニューロンアクターネットワーク
A Quadratic Actor Network for Model-Free Reinforcement Learning
方策ネットワークに二次ニューロンを組み込み、従来のMLPより少ないパラメータで高い報酬とサンプル効率を実現した。
著者: Matthias Weissenbacher, Yoshinobu Kawahara
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
In this work we discuss the incorporation of quadratic neurons into policy networks in the context of model-free actor-critic reinforcement learning. Quadratic neurons admit an explicit quadratic function approximation in contrast to conventional approaches where the the non-linearity is induced by the activation functions. We perform empiric experiments on several MuJoCo continuous control tasks and find that when quadratic neurons are added to MLP policy networks those outperform the baseline MLP whilst admitting a smaller number of parameters. The top returned reward is in average increased by $5.8\%$ while being about $21\%$ more sample efficient. Moreover, it can maintain its advantage against added action and observation noise.
