Year: 2018
Type: preprint
Abstract: Reinforcement Learning (RL) algorithms can suffer from poor sample efficiency when rewards are delayed and sparse. We introduce a solution that enables agents to learn temporally extended actions at multiple levels of abstraction in a sample efficient and automated fashion. Our approach combines universal value functions and hindsight learning, allowing agents to learn policies belonging to different time scales in parallel. We show that our method significantly accelerates learning in a variety of discrete and continuous tasks.
Source: arXiv (Cornell University)
Authors: Levy, Andrew, Platt, Robert, Saenko, Kate
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2804672169