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: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2012-09-01
|
| Series: | Paladyn: Journal of Behavioral Robotics |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/s13230-013-0108-6 |