2022/10/06 by Bryon Tjanaka, Tjanaka, Bryon, Matthew C. Fontaine +6 · 3 citations
Computer Science · Engineering · #FOS: Computer and information sciences #Human Pose and Action Recognition #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Reinforcement Learning in Robotics #Robotic Locomotion and Control #Robotics (cs.RO)
paper · pdf · doi:10.48550/arxiv.2210.02622
openalex publication_date 2022/10/06 · openalex created_date 2023/02/13 · openalex updated_date 2026/07/28
Pre-training a diverse set of neural network controllers in simulation has enabled robots to adapt online to damage in robot locomotion tasks. However, finding diverse, high-performing controllers requires expensive network training and extensive tuning of a large number of hyperparameters. On the other hand, Covariance Matrix Adaptation MAP-Annealing (CMA-MAE), an evolution strategies (ES)-based quality diversity algorithm, does not have these limitations and has achieved state-of-the-art performance on standard QD benchmarks. However, CMA-MAE cannot scale to modern neural network controllers due to its quadratic complexity. We leverage efficient approximation methods in ES to propose three new CMA-MAE variants that scale to high dimensions. Our experiments show that the variants outperform ES-based baselines in benchmark robotic locomotion tasks, while being comparable with or exceeding state-of-the-art deep reinforcement learning-based quality diversity algorithms.