[D-20] 情報論的学習理論と機械学習

11:45 AM - 12:00 PM JST(2:45 AM - 3:00 AM UTC)

[D-20-11] Model-based Reinforcement Learning by Predicting Various States through Latent Variable Editing

○Yuta Horiuchi¹, Hisashi Handa¹, Kimihiro Mizutani¹, Kimiaki Shirahama² (1. Kindai Univ., 2. Doshisha Univ.)

Keywords:

Reinforcement Learning,Model-based Reinforcement Learning,Data Augmentation