Benchmarking projective simulation in navigation problems

Cite This

Files in this item

Checksum: MD5:45d0d548a0d627ac3d47012b059d1f30

MELNIKOV, Alexey A., Adi MAKMAL, Hans J. BRIEGEL, 2018. Benchmarking projective simulation in navigation problems. In: IEEE Access. 6, pp. 64639-64648. eISSN 2169-3536. Available under: doi: 10.1109/ACCESS.2018.2876494

@article{Melnikov2018-04-23T17:58:27ZBench-45506, title={Benchmarking projective simulation in navigation problems}, year={2018}, doi={10.1109/ACCESS.2018.2876494}, volume={6}, journal={IEEE Access}, pages={64639--64648}, author={Melnikov, Alexey A. and Makmal, Adi and Briegel, Hans J.} }

<rdf:RDF xmlns:dcterms="http://purl.org/dc/terms/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:bibo="http://purl.org/ontology/bibo/" xmlns:dspace="http://digital-repositories.org/ontologies/dspace/0.1.0#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:void="http://rdfs.org/ns/void#" xmlns:xsd="http://www.w3.org/2001/XMLSchema#" > <rdf:Description rdf:about="https://kops.uni-konstanz.de/rdf/resource/123456789/45506"> <dspace:isPartOfCollection rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/40"/> <dcterms:issued>2018-04-23T17:58:27Z</dcterms:issued> <dc:creator>Makmal, Adi</dc:creator> <dcterms:rights rdf:resource="https://kops.uni-konstanz.de/page/termsofuse"/> <dc:creator>Briegel, Hans J.</dc:creator> <dcterms:hasPart rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45506/1/Melnikov_2-uacj9ekdo4vr5.pdf"/> <dcterms:abstract xml:lang="eng">Projective simulation (PS) is a model for intelligent agents with a deliberation capacity that is based on episodic memory. The model has been shown to provide a flexible framework for constructing reinforcement-learning agents, and it allows for quantum mechanical generalization, which leads to a speed-up in deliberation time. PS agents have been applied successfully in the context of complex skill learning in robotics, and in the design of state-of-the-art quantum experiments. In this paper, we study the performance of projective simulation in two benchmarking problems in navigation, namely the grid world and the mountain car problem. The performance of PS is compared to standard tabular reinforcement learning approaches, Q-learning and SARSA. Our comparison demonstrates that the performance of PS and standard learning approaches are qualitatively and quantitatively similar, while it is much easier to choose optimal model parameters in case of projective simulation, with a reduced computational effort of one to two orders of magnitude. Our results show that the projective simulation model stands out for its simplicity in terms of the number of model parameters, which makes it simple to set up the learning agent in unknown task environments.</dcterms:abstract> <dc:language>eng</dc:language> <dc:creator>Melnikov, Alexey A.</dc:creator> <dc:contributor>Briegel, Hans J.</dc:contributor> <dc:contributor>Makmal, Adi</dc:contributor> <dspace:hasBitstream rdf:resource="https://kops.uni-konstanz.de/bitstream/123456789/45506/1/Melnikov_2-uacj9ekdo4vr5.pdf"/> <dcterms:title>Benchmarking projective simulation in navigation problems</dcterms:title> <bibo:uri rdf:resource="https://kops.uni-konstanz.de/handle/123456789/45506"/> <dc:rights>terms-of-use</dc:rights> <foaf:homepage rdf:resource="http://localhost:8080/jspui"/> <dc:date rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-03-18T14:43:50Z</dc:date> <dcterms:available rdf:datatype="http://www.w3.org/2001/XMLSchema#dateTime">2019-03-18T14:43:50Z</dcterms:available> <dc:contributor>Melnikov, Alexey A.</dc:contributor> <void:sparqlEndpoint rdf:resource="http://localhost/fuseki/dspace/sparql"/> <dcterms:isPartOf rdf:resource="https://kops.uni-konstanz.de/rdf/resource/123456789/40"/> </rdf:Description> </rdf:RDF>

Downloads since Mar 18, 2019 (Information about access statistics)

Melnikov_2-uacj9ekdo4vr5.pdf 26

This item appears in the following Collection(s)

Search KOPS


Browse

My Account