University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Auto-Perceptive Reinforcement Learning (APRiL)

Allday, Rebecca, Hadfield, Simon and Bowden, Richard (2019) Auto-Perceptive Reinforcement Learning (APRiL) In: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2019), 04-08 Nov 2019, The Venetian Macao, Macau, China.

[img]
Preview
Text
Auto-Perceptive Reinforcement Learning (APRiL).pdf - Accepted version Manuscript

Download (993kB) | Preview

Abstract

The relationship between the feedback given in Reinforcement Learning (RL) and visual data input is often extremely complex. Given this, expecting a single system trained end-to-end to learn both how to perceive and interact with its environment is unrealistic for complex domains. In this paper we propose Auto-Perceptive Reinforcement Learning (APRiL), separating the perception and the control elements of the task. This method uses an auto-perceptive network to encode a feature space. The feature space may explicitly encode available knowledge from the semantically understood state space but the network is also free to encode unanticipated auxiliary data. By decoupling visual perception from the RL process, APRiL can make use of techniques shown to improve performance and efficiency of RL training, which are often difficult to apply directly with a visual input. We present results showing that APRiL is effective in tasks where the semantically understood state space is known. We also demonstrate that allowing the feature space to learn auxiliary information, allows it to use the visual perception system to improve performance by approximately 30%. We also show that maintaining some level of semantics in the encoded state, which can then make use of state-of-the art RL techniques, saves around 75% of the time that would be used to collect simulation examples.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Allday, Rebeccar.allday@surrey.ac.uk
Hadfield, Simons.hadfield@surrey.ac.uk
Bowden, RichardR.Bowden@surrey.ac.uk
Date : 2019
Copyright Disclaimer : © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Related URLs :
Depositing User : Clive Harris
Date Deposited : 26 Sep 2019 10:52
Last Modified : 04 Nov 2019 02:08
URI: http://epubs.surrey.ac.uk/id/eprint/852812

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800