Effect of Viewing Directions on Deep Reinforcement Learning in 3D Virtual Environment Minecraft

この論文をさがす

説明

Deep reinforcement learning, which has recently attracted the interest of AI researchers, combines deep neural networks (DNNs) and reinforcement learning (RL). By approximating a function in RL with a DNN, it enables an agent to learn in a complex environment rep- resented by low-level features such as the pixels used in a 3D video game. However, learning from low-level features is sometimes problematic. For example, a small difference in input pixels results in completely different behaviors of an agent. In this study, as an example of such problems, we focus on the viewing directions of an agent in a 3D virtual environment (Minecraft) and analyze their effect on the efficiency of deep reinforce- ment learning.

収録刊行物

詳細情報 詳細情報について

  • CRID
    1050282677652881792
  • NII論文ID
    120006695568
  • DOI
    10.1007/978-3-030-03098-8_38
  • ISSN
    16113349
    03029743
  • HANDLE
    2115/72064
  • 本文言語コード
    en
  • 資料種別
    conference paper
  • データソース種別
    • IRDB
    • CiNii Articles
    • OpenAIRE

問題の指摘

ページトップへ