Please use this identifier to cite or link to this item:
http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6685Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.creator | Finney, Sarah | - |
| dc.creator | Gardiol, Natalia H. | - |
| dc.creator | Kaelbling, Leslie Pack | - |
| dc.creator | Oates, Tim | - |
| dc.date | 2004-10-08T20:37:45Z | - |
| dc.date | 2004-10-08T20:37:45Z | - |
| dc.date | 2002-04-10 | - |
| dc.date.accessioned | 2013-10-09T02:46:27Z | - |
| dc.date.available | 2013-10-09T02:46:27Z | - |
| dc.date.issued | 2013-10-09 | - |
| dc.identifier | AIM-2002-006 | - |
| dc.identifier | http://hdl.handle.net/1721.1/6685 | - |
| dc.identifier.uri | http://koha.mediu.edu.my:8181/xmlui/handle/1721 | - |
| dc.description | Most reinforcement learning methods operate on propositional representations of the world state. Such representations are often intractably large and generalize poorly. Using a deictic representation is believed to be a viable alternative: they promise generalization while allowing the use of existing reinforcement-learning methods. Yet, there are few experiments on learning with deictic representations reported in the literature. In this paper we explore the effectiveness of two forms of deictic representation and a naive propositional representation in a simple blocks-world domain. We find, empirically, that the deictic representations actually worsen performance. We conclude with a discussion of possible causes of these results and strategies for more effective learning in domains with objects. | - |
| dc.format | 41 p. | - |
| dc.format | 5712208 bytes | - |
| dc.format | 1294450 bytes | - |
| dc.format | application/postscript | - |
| dc.format | application/pdf | - |
| dc.language | en_US | - |
| dc.relation | AIM-2002-006 | - |
| dc.subject | AI | - |
| dc.subject | Reinforcement Learning | - |
| dc.subject | Partial Observability | - |
| dc.subject | Representations | - |
| dc.title | Learning with Deictic Representation | - |
| Appears in Collections: | MIT Items | |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.