Actor-Criticを用いた遺伝的ネットワークプログラミングの小型移動ロボットの行動生成における性能評価

DOI Web Site

書誌事項

タイトル別名
  • Performance Evaluation of Genetic Network Programming with Actor-Critic for Creating Mobile Robot Behavior

抄録

Genetic Network Programming (GNP) has been proposed as a new graph-based evolutionary algorithm. GNP represents its solutions as graph structures which contribute to improving the expression ability of the programs. GNP with Reinforcement Learning (GNP-RL) was also proposed as an extended algorithm of GNP and its effectiveness has been confirmed. Because GNP-RL executes reinforcement learning during task execution in addition to evolution after task execution, it can search for solutions efficiently. In this paper, GNP with Actor-Critic (GNP-AC) is proposed to enhance the effectiveness of GNP-RL. Actor-Critic can adjust numerical values appropriately during task execution, i. e., online learning, and use them for determining actions. To confirm the effectiveness of the proposed method, GNP-AC is applied to the controller of the Khepera simulator and its generalization ability is evaluated.

収録刊行物

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