ロボット制御のための深層神経進化における品質多様性アルゴリズムのベンチマーク
Benchmarking Quality-Diversity Algorithms on Neuroevolution for Reinforcement Learning
ロボット制御の強化学習領域で深層神経進化に品質多様性アルゴリズムを適用するためのベンチマークスイートを提案し、標準的な評価指標と環境の確率性に対するロバスト性の定量化手法を提示した。
著者: Manon Flageat, Bryan Lim, Luca Grillotti, Maxime Allard, Simón C. Smith, Antoine Cully
分類: cs.NE, cs.AI, cs.LG, cs.RO
原文アブストラクト
We present a Quality-Diversity benchmark suite for Deep Neuroevolution in Reinforcement Learning domains for robot control. The suite includes the definition of tasks, environments, behavioral descriptors, and fitness. We specify different benchmarks based on the complexity of both the task and the agent controlled by a deep neural network. The benchmark uses standard Quality-Diversity metrics, including coverage, QD-score, maximum fitness, and an archive profile metric to quantify the relation between coverage and fitness. We also present how to quantify the robustness of the solutions with respect to environmental stochasticity by introducing corrected versions of the same metrics. We believe that our benchmark is a valuable tool for the community to compare and improve their findings. The source code is available online: https://github.com/adaptive-intelligent-robotics/QDax
