Accelerating reinforcement learning with a directional-Gaussian-smoothing evolution strategy

DOI10.3934/era.2021075zbMath1484.37099arXiv2002.09077OpenAlexW3200056662MaRDI QIDQ2055215

Yanyan Li

Publication date: 3 December 2021

Published in: Electronic Research Archive (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2002.09077

zbMATH Keywords

stochastic controlreinforcement learningnon-convex optimizationGauss-Hermite quadratureGaussian smoothinghigh-dimensional optimization

Mathematics Subject Classification ID

Continuous-time Markov processes on general state spaces (60J25) Learning and adaptive systems in artificial intelligence (68T05) Stochastic learning and adaptive control (93E35) Approximation methods and numerical treatment of dynamical systems (37M99)

Uses Software

• CMA-ES
• OpenAI Gym
• PyTorch
• GitHub
• Ray
• Baselines
• Pybullet

Cites Work

• Enhanced variable-fidelity surrogate-based optimization framework by Gaussian process regression and fuzzy clustering
• Random gradient-free minimization of convex functions
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Accelerating reinforcement learning with a directional-Gaussian-smoothing evolution strategy