Sparse kernel-SARSA(lambda) with an eligibility trace
| dc.contributor.author | Robards, Matthew | |
| dc.contributor.author | Sunehag, Peter | |
| dc.contributor.author | Sanner, Scott | |
| dc.contributor.author | Marthi, Bhaskara | |
| dc.coverage.spatial | Athens Greece | |
| dc.date.accessioned | 2015-12-13T22:58:18Z | |
| dc.date.created | September 5-9 2011 | |
| dc.date.issued | 2011 | |
| dc.date.updated | 2016-02-24T08:39:02Z | |
| dc.description.abstract | We introduce the first online kernelized version of SARSA(λ) to permit sparsification for arbitrary λ for 0 ≤ λ ≤ 1; this is possible via a novel kernelization of the eligibility trace that is maintained separately from the kernelized value functio | |
| dc.identifier.isbn | 9783642237799 | |
| dc.identifier.uri | http://hdl.handle.net/1885/83410 | |
| dc.publisher | Springer | |
| dc.relation.ispartofseries | Machine Learning and Knowledge Discovery in Databases European Conference (ECML PKDD 2011) | |
| dc.source | Proceedings of Machine Learning and Knowledge Discovery in Databases - European Conference (ECML PKDD 2011) | |
| dc.subject | Keywords: Basis functions; Capacity control; Eligibility traces; Functional structure; Kernelization; Memory efficiency; Projection techniques; Sparse kernels; Sparsification; Value functions; Learning systems | |
| dc.title | Sparse kernel-SARSA(lambda) with an eligibility trace | |
| dc.type | Conference paper | |
| local.bibliographicCitation.lastpage | 17 | |
| local.bibliographicCitation.startpage | 1 | |
| local.contributor.affiliation | Robards, Matthew, College of Engineering and Computer Science, ANU | |
| local.contributor.affiliation | Sunehag, Peter, College of Engineering and Computer Science, ANU | |
| local.contributor.affiliation | Sanner, Scott, College of Engineering and Computer Science, ANU | |
| local.contributor.affiliation | Marthi, Bhaskara, Willow Garage Inc. | |
| local.contributor.authoruid | Robards, Matthew, u4583807 | |
| local.contributor.authoruid | Sunehag, Peter, u4753099 | |
| local.contributor.authoruid | Sanner, Scott, u1817461 | |
| local.description.embargo | 2037-12-31 | |
| local.description.notes | Imported from ARIES | |
| local.description.refereed | Yes | |
| local.identifier.absfor | 080109 - Pattern Recognition and Data Mining | |
| local.identifier.absfor | 080303 - Computer System Security | |
| local.identifier.ariespublication | f5625xPUB11671 | |
| local.identifier.doi | 10.1007/978-3-642-23808-6_1 | |
| local.identifier.scopusID | 2-s2.0-80052398950 | |
| local.type.status | Published Version |
Downloads
Original bundle
1 - 1 of 1
Loading...
- Name:
- 01_Robards_Sparse_kernel-SARSA(lambda)_2011.pdf
- Size:
- 454.8 KB
- Format:
- Adobe Portable Document Format