深層強化学習とDeep Neuroevolution によるロボティックスワームの群れ行動生成と解析

DOI Web Site Web Site 参考文献5件

書誌事項

タイトル別名
  • Generating and Analyzing Collective Behavior in a Robotic Swarm by the Use of Deep Reinforcement Learning and Deep Neuroevolution
  • シンソウ キョウカ ガクシュウ ト Deep Neuroevolution ニ ヨル ロボティックスワーム ノ ムレ コウドウ セイセイ ト カイセキ

この論文をさがす

抄録

<p>This study proposes a method to apply deep neural networks to controllers of robotic swarms. In a typical approach to design controllers, the designer has to define the features extracted from sensory inputs in advance. By applying deep neural networks with convolution layers, it can automatically extract features from sensory inputs. We applied two methods to train the deep neural networks, i.e.,deep reinforcement learning and deep neuroevolution. The controllers were tested in a path-formation task using computer simulations. Compared with deep reinforcement learning, deep neuroevolution was able to generate collective behavior even in sparse reward settings.</p>

収録刊行物

参考文献 (5)*注記

もっと見る

関連プロジェクト

もっと見る

キーワード

詳細情報 詳細情報について

問題の指摘

ページトップへ