Year: 2019
Type: preprint
Abstract: Humans and animals solve a difficult problem much more easily when they are presented with a sequence of problems that starts simple and slowly increases in difficulty. We explore this idea in the context of reinforcement learning. Rather than providing the agent with an externally provided curriculum of progressively more difficult tasks, the agent solves a single task utilizing a decreasingly constrained policy space. The algorithm we propose first learns to categorize features into positive and negative before gradually learning a more refined policy. Experimental results in Tetris demonstrate superior learning rate of our approach when compared to existing algorithms.
Source: arXiv (Cornell University)
Authors: Lichtenberg, Jan Malte, Şimşek, Özgür
Institution: University of Bath
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2991758148