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

DOI IR (HANDLE) Open Access

Search this article

Description

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.

Journal

Details 詳細情報について

  • CRID
    1050282677652881792
  • NII Article ID
    120006695568
  • DOI
    10.1007/978-3-030-03098-8_38
  • ISSN
    16113349
    03029743
  • HANDLE
    2115/72064
  • Text Lang
    en
  • Article Type
    conference paper
  • Data Source
    • IRDB
    • CiNii Articles
    • OpenAIRE

Report a problem

Back to top