Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning

Nat Dilokthanakul
Nat Dilokthanakul
Christos Kaplanis
Christos Kaplanis
Nick Pawlowski
Nick Pawlowski

IEEE Transactions on Neural Networks and Learning Systems, Volume abs/1705.06769, Issue 11, 2019, Pages 3409-3418.

Cited by: 26|Bibtex|Views4|Links
EI WOS
Keywords:
Task analysisReinforcement learningTrainingNeural networksVisualizationMore(2+)

Abstract:

One of the main concerns of deep reinforcement learning (DRL) is the data inefficiency problem, which stems both from an inability to fully utilize data acquired and from naive exploration strategies. In order to alleviate these problems, we propose a DRL algorithm that aims to improve data efficiency via both the utilization of unrewarde...More

Code:

Data:

Your rating :
0

 

Tags
Comments