A Quadratic Actor Network for Model-Free Reinforcement Learning

Autor:	Weissenbacher, Matthias, Kawahara, Yoshinobu
Rok vydání:	2021
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Robotics
Druh dokumentu:	Working Paper
Popis:	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. Comment: 8 pages, 15 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2103.06617 Zobrazit plný text záznamu View this record from Arxiv