We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Adaptive exploration through covariance matrix adaptation enables developmental motor learning.
- Authors
Stulp, Freek; Oudeyer, Pierre-Yves
- Abstract
The 'Policy Improvement with Path Integrals' (PI) [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 adaptation into PI- which yields the PI algorithm - enables adaptive exploration by continually and autonomously reconsidering the exploration/exploitation trade-off. In this article, we provide an overview of our recent work on covariance matrix adaptation for direct reinforcement learning [22-24], highlight its relevance to developmental robotics, and conduct further experiments to analyze the results. We investigate two complementary phenomena from developmental robotics. First, we demonstrate PI's ability to adapt to slowly or abruptly changing tasks due to its continual and adaptive exploration. This is an important component of life-long skill learning in dynamic environments. Second, we show on a reaching task how PI subsequently releases degrees of freedom from proximal to more distal limbs as learning progresses. A similar effect is observed in human development, where it is known as 'proximodistal maturation'.
- Publication
Paladyn: Journal of Behavioral Robotics, 2012, Vol 3, Issue 3, p128
- ISSN
2080-9778
- Publication type
Article
- DOI
10.2478/s13230-013-0108-6