Imperial College London
Portrait Picture

ProfessorAlessandraRusso

Faculty of Engineering, Department of Computing

Professor in Applied Computational Logic
 
 
 
//

Contact

 

+44 (0)20 7594 8312a.russo Website

 
 
//

Location

 

560Huxley BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Mitchener:2022:10.1007/s10994-022-06142-7,
author = {Mitchener, L and Tuckey, D and Crosby, M and Russo, A},
doi = {10.1007/s10994-022-06142-7},
journal = {Machine Learning},
pages = {1523--1549},
title = {Detect, understand, act: a neuro-symbolic hierarchical reinforcement learning framework},
url = {http://dx.doi.org/10.1007/s10994-022-06142-7},
volume = {111},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - In this paper we introduce Detect, Understand, Act (DUA), a neuro-symbolic reinforcement learning framework. The Detect component is composed of a traditional computer vision object detector and tracker. The Act component houses a set of options, high-level actions enacted by pre-trained deep reinforcement learning (DRL) policies. The Understand component provides a novel answer set programming (ASP) paradigm for symbolically implementing a meta-policy over options and effectively learning it using inductive logic programming (ILP). We evaluate our framework on the Animal-AI (AAI) competition testbed, a set of physical cognitive reasoning problems. Given a set of pre-trained DRL policies, DUA requires only a few examples to learn a meta-policy that allows it to improve the state-of-the-art on multiple of the most challenging categories from the testbed. DUA constitutes the first holistic hybrid integration of computer vision, ILP and DRL applied to an AAI-like environment and sets the foundations for further use of ILP in complex DRL challenges.
AU  - Mitchener,L
AU  - Tuckey,D
AU  - Crosby,M
AU  - Russo,A
DO  - 10.1007/s10994-022-06142-7
EP  - 1549
PY  - 2022///
SN  - 0885-6125
SP  - 1523
TI  - Detect, understand, act: a neuro-symbolic hierarchical reinforcement learning framework
T2  - Machine Learning
UR  - http://dx.doi.org/10.1007/s10994-022-06142-7
UR  - https://link.springer.com/article/10.1007/s10994-022-06142-7
UR  - http://hdl.handle.net/10044/1/96353
VL  - 111
ER  -
Download