Global versus local constructive function approximation for on-line reinforcement learning
P Vamplew, R Ollington - Australasian Joint Conference on Artificial …, 2005 - Springer
In order to scale to large state-spaces, reinforcement learning (RL) algorithms need to apply
function approximation techniques. Research on function approximation for RL has so far …
function approximation techniques. Research on function approximation for RL has so far …
To the knowledge frontier and beyond: A hybrid system for incremental contextual-learning and prudence analysis
RP Dazeley - 2006 - figshare.utas.edu.au
Increasingly, researchers and developers of knowledge based systems (KBS) have been
attempting to incorporate the notion of context. For instance, Repertory Grids, Formal …
attempting to incorporate the notion of context. For instance, Repertory Grids, Formal …
Learning place cells from sonar data
R Ollington, P Vamplew - 2004 - figshare.utas.edu.au
A place cell system is developed that is able to provide\robust localisation using simple
sonar information only.\The system uses egocentric view cells, based on the\Adaptive …
sonar information only.\The system uses egocentric view cells, based on the\Adaptive …
Localisation and navigation: applying biological principles in mobile robotics
R Ollington - 2007 - figshare.utas.edu.au
Recently, there has been a significant effort to apply behavioural and anatomical studies
ofhippocampal place learning in rodents and other animals to the problem of robot …
ofhippocampal place learning in rodents and other animals to the problem of robot …
[PDF][PDF] To The Knowledge Frontier and Beyond
RP Dazeley - University of Tasmania, 2006 - researchgate.net
Increasingly, researchers and developers of knowledge based systems (KBS) have been
attempting to incorporate the notion of context. For instance, Repertory Grids, Formal …
attempting to incorporate the notion of context. For instance, Repertory Grids, Formal …