Abstraction Networks

Lead Research Organisation: Imperial College London
Department Name: Dept of Computing

Abstract

A Method For Knowledge Extraction Towards Lifelong
Reinforcement Learning

. Due to the requirement of autonomy, this project examines progress made in Lifelong
Reinforcement Learning (LRL) and identifies a promising development direction in the use
of technologies which incorporate a relational inductive bias over the knowledge representations. Finally, by integrating two prominent methods, namely Graph Networks and Latent
Feature Models, Abstraction Networks are proposed as a potential LRL framework, as they
assume a network of fundamental state-abstractions that have inherent synergy with the
knowledge manipulation requirements of lifelong learning.

Research area Reinforcement learning

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
EP/N509486/1 01/10/2016 30/09/2021
2286911 Studentship EP/N509486/1 01/04/2017 30/09/2021 Herald Selim Stromfelt