Contextual Covariance Matrix Adaptation Evolutionary Strategies

• Type: Article in International Conference Proceedings Book
• Date: 2017

Authors

Abdolmaleki, A (Author) Other; Price, B (Author) Other; lau, n (Author) FCUP; reis, lp (Author) REIT; Neumann, G (Author) Other

Conference proceedings International

Title: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI 2017, Melbourne, Australia, August 19-25, 2017

Pages: 1378-1385

26th International Joint Conference on Artificial Intelligence, IJCAI 2017

19 August 2017 through 25 August 2017

Indexing

Scopus - 4 Citations

Other information

Authenticus ID: P-00M-YKF

DOI: 10.24963/ijcai.2017/191

Abstract (EN): Many stochastic search algorithms are designed to optimize a fixed objective function to learn a task, i.e., if the objective function changes slightly, for example, due to a change in the situation or context of the task, relearning is required to adapt to the new context. For instance, if we want to learn a kicking movement for a soccer robot, we have to relearn the movement for different ball locations. Such relearning is undesired as it is highly inefficient and many applications require a fast adaptation to a new context/situation. Therefore, we investigate contextual stochastic search algorithms that can learn multiple, similar tasks simultaneously. Current contextual stochastic search methods are based on policy search algorithms and suffer from premature convergence and the need for parameter tuning. In this paper, we extend the well known CMA-ES algorithm to the contextual setting and illustrate its performance on several contextual tasks. Our new algorithm, called contextual CMAES, leverages from contextual learning while it preserves all the features of standard CMA-ES such as stability, avoidance of premature convergence, step size control and a minimal amount of parameter tuning.

Language: English

Type (Professor's evaluation): Scientific