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

The Journey is the Reward: Unsupervised Learning of Influential Trajectories

2019-05-22
Jonathan Binas, Sherjil Ozair, Yoshua Bengio

Abstract

Unsupervised exploration and representation learning become increasingly important when learning in diverse and sparse environments. The information-theoretic principle of empowerment formalizes an unsupervised exploration objective through an agent trying to maximize its influence on the future states of its environment. Previous approaches carry certain limitations in that they either do not employ closed-loop feedback or do not have an internal state. As a consequence, a privileged final state is taken as an influence measure, rather than the full trajectory. We provide a model-free method which takes into account the whole trajectory while still offering the benefits of option-based approaches. We successfully apply our approach to settings with large action spaces, where discovery of meaningful action sequences is particularly difficult.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1905.09334

PDF

http://arxiv.org/pdf/1905.09334


Similar Posts

Comments