行動変異による大規模並列化で方策勾配品質多様性をスケーリング
Scaling Policy Gradient Quality-Diversity with Massive Parallelization via Behavioral Variations
MAP-Elitesを方策勾配で拡張し、集中型actor-criticに依存せず大規模並列化可能にしたASCII-MEを提案。単一GPUで250秒未満に高性能な多様方策群を生成し、既存手法より平均5倍高速。
著者: Konstantinos Mitsides, Maxence Faldor, Antoine Cully
分類: cs.NE, cs.AI, cs.LG, cs.RO
原文アブストラクト
Quality-Diversity optimization comprises a family of evolutionary algorithms aimed at generating a collection of diverse and high-performing solutions. MAP-Elites (ME), a notable example, is used effectively in fields like evolutionary robotics. However, the reliance of ME on random mutations from Genetic Algorithms limits its ability to evolve high-dimensional solutions. Methods proposed to overcome this include using gradient-based operators like policy gradients or natural evolution strategies. While successful at scaling ME for neuroevolution, these methods often suffer from slow training speeds, or difficulties in scaling with massive parallelization due to high computational demands or reliance on centralized actor-critic training. In this work, we introduce a fast, sample-efficient ME based algorithm capable of scaling up with massive parallelization, significantly reducing runtimes without compromising performance. Our method, ASCII-ME, unlike existing policy gradient quality-diversity methods, does not rely on centralized actor-critic training. It performs behavioral variations based on time step performance metrics and maps these variations to solutions using policy gradients. Our experiments show that ASCII-ME can generate a diverse collection of high-performing deep neural network policies in less than 250 seconds on a single GPU. Additionally, it operates on average, five times faster than state-of-the-art algorithms while still maintaining competitive sample efficiency.
