papers AI Learner
The Github is limit! Click to go to the new site.

An Optimization Framework for Task Sequencing in Curriculum Learning

2019-01-31
Francesco Foglino, Matteo Leonetti

Abstract

Curriculum learning is gaining popularity in (deep) reinforcement learning. It can alleviate the burden on data collection and provide better exploration policies through transfer and generalization from less complex tasks. Current methods for automatic task sequencing for curriculum learning in reinforcement learning provided initial heuristic solutions, with little to no guarantee on their quality. We introduce an optimization framework for task sequencing composed of the problem definition, several candidate performance metrics for optimization, and three benchmark algorithms. We experimentally show that the two most commonly used baselines (learning with no curriculum, and with a random curriculum) perform worse than a simple greedy algorithm. Furthermore, we show theoretically and demonstrate experimentally that the three proposed algorithms provide increasing solution quality at moderately increasing computational complexity, and show that they constitute better baselines for curriculum learning in reinforcement learning.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.11478

PDF

http://arxiv.org/pdf/1901.11478


Similar Posts

Comments