The Hierarchical Continuous Pursuit Learning Automation: A Novel Scheme for Environments With Large Numbers of Actions
Journal article, Peer reviewed
Accepted version
Permanent lenke
https://hdl.handle.net/10642/8102Utgivelsesdato
2019Metadata
Vis full innførselSamlinger
Originalversjon
Yazidi A, Zhang X, Lei J, Oommen J. The Hierarchical Continuous Pursuit Learning Automation: A Novel Scheme for Environments With Large Numbers of Actions. IEEE Transactions on Neural Networks and Learning Systems. 2019 https://dx.doi.org/10.1109/TNNLS.2019.2905162Sammendrag
Although the field of learning automata (LA) has made significant progress in the past four decades, the LA-based methods to tackle problems involving environments with a large number of actions is, in reality, relatively unresolved. The extension of the traditional LA to problems within this domain cannot be easily established when the number of actions is very large. This is because the dimensionality of the action probability vector is correspondingly large, and so, most components of the vector will soon have values that are smaller than the machine accuracy permits, implying that they will never be chosen . This paper presents a solution that extends the continuous pursuit paradigm to such large -actioned problem domains. The beauty of the solution is that it is hierarchical, where all the actions offered by the environment reside as leaves of the hierarchy. Furthermore, at every level, we merely require a two -action LA that automatically resolves the problem of dealing with arbitrarily small action probabilities. In addition, since all the LA invoke the pursuit paradigm, the best action at every level trickles up toward the root. Thus, by invoking the property of the “max” operator, in which the maximum of numerous maxima is the overall maximum, the hierarchy of LA converges to the optimal action. This paper describes the scheme and formally proves its $\epsilon $ -optimal convergence. The results presented here can, rather trivially, be extended for the families of discretized and Bayesian pursuit LA too. This paper also reports extensive experimental results (including for environments having 128 and 256 actions) that demonstrate the power of the scheme and its computational advantages. As far as we know, there are no comparable pursuit-based results in the field of LA . In some cases, the hierarchical continuous pursuit automaton requires less than 18% of the number of iterations than the benchmark $L_{R-I}$ scheme, which is, by all metrics, phenomenal .
Utgiver
Institute of Electrical and Electronics Engineers (IEEE)Serie
IEEE Transactions on Neural Networks and Learning Systems;Volume: 31, Issue: 2Tidsskrift
IEEE Transactions on Neural Networks and Learning SystemsBeslektede innførsler
Viser innførsler beslektet ved tittel, forfatter og emneord.
-
The Hierarchical Continuous Pursuit Learning Automation for Large Numbers of Actions
Yazidi, Anis; Zhang, Xuan; Lei, Jiao; Oommen, John (Chapter; Peer reviewed, 2018-05-22)Although the field of Learning Automata (LA) has made significant progress in the last four decades, the LA-based methods to tackle problems involving environments with a large number of actions are, in reality, relatively ... -
Arts-based learning in vocational education: Using arts-based approaches to enrich vocational pedagogy and didactics and to enhance professional competence and identity
Meltzer, Cecilie; Schwencke, Eva (Journal of Adult and Continuing Education;2019, Journal article; Peer reviewed, 2019)This article discusses in what way arts-based learning can complement and enrich vocational pedagogy and didactics. It examines how artwork and artistic, educational practices can enhance professional and vocational skills, ... -
Associations between workplace learning patterns, social support and perceived competency
Sadeghi, Talieh (Human Resource Development International;Volume 23, 2020 - Issue 1, Journal article; Peer reviewed, 2019-06-01)Despite substantial research in the field of workplace learning and training over the past three decades, these concepts are heavily under-researched in relation to the public sector. By means of survey data, this study ...