Adaptive Exploration through Covariance Matrix Adaptation Enables Developmental Motor Learning
The “Policy Improvement with Path Integrals” (PI2) [25] and “Covariance Matrix Adaptation - Evolutionary Strategy” [8] are considered to be state-of-the-art in direct reinforcement learning and stochastic optimization respectively. We have recently shown that incorporating covariance matrix adaptati...
Main Authors: | Stulp Freek, Oudeyer Pierre-Yves |
---|---|
Format: | Article |
Language: | English |
Published: |
De Gruyter
2012-09-01
|
Series: | Paladyn |
Subjects: | |
Online Access: | https://doi.org/10.2478/s13230-013-0108-6 |
Similar Items
-
An Adaptive Mechanism With Cooperative Coevolution and Covariance for Differential Evolution
by: Bin Wang, et al.
Published: (2021-01-01) -
Application of Covariance Matrix Adaptation-Evolution Strategy to Optimal Portfolio
by: S. Amir Ghoreishi, et al.
Published: (2019-04-01) -
An Investigation of Adaptive Radius for the Covariance Localization in Ensemble Data Assimilation
by: Xiang Xing, et al.
Published: (2021-10-01) -
Comparison of Pocock and Simon’s covariate-adaptive randomization procedures in clinical trials
by: Guogen Shan, et al.
Published: (2024-01-01) -
Clutter Covariance Matrix Estimation for Radar Adaptive Detection Based on a Complex-Valued Convolutional Neural Network
by: Naixin Kang, et al.
Published: (2023-11-01)