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

Hierarchical Reinforcement Learning with Hindsight

2019-03-08
Andrew Levy, Robert Platt, Kate Saenko

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1805.08180

PDF

http://arxiv.org/e-print/1805.08180


Similar Posts

Comments