自律エージェントの状態行動マッピングに向けた神経回路網トポロジーの適応的ゲノム進化
Adaptive Genomic Evolution of Neural Network Topologies (AGENT) for State-to-Action Mapping in Autonomous Agents
NEATを改良し、集団の多様性と平均適合度の改善を自動制御することで早期停滞と収束問題に対処する神経進化アルゴリズムAGENTを提案し、OpenAIの3ベンチマークとUAV衝突回避問題で評価した。
著者: Amir Behjat, Sharat Chidambaran, Souma Chowdhury
分類: cs.NE, cs.AI, cs.RO
原文アブストラクト
Neuroevolution is a process of training neural networks (NN) through an evolutionary algorithm, usually to serve as a state-to-action mapping model in control or reinforcement learning-type problems. This paper builds on the Neuro Evolution of Augmented Topologies (NEAT) formalism that allows designing topology and weight evolving NNs. Fundamental advancements are made to the neuroevolution process to address premature stagnation and convergence issues, central among which is the incorporation of automated mechanisms to control the population diversity and average fitness improvement within the neuroevolution process. Insights into the performance and efficiency of the new algorithm is obtained by evaluating it on three benchmark problems from the Open AI platform and an Unmanned Aerial Vehicle (UAV) collision avoidance problem.
