Please use this identifier to cite or link to this item:
http://dspace.mediu.edu.my:8181/xmlui/handle/1721.1/6076| Title: | Exploration in Gradient-Based Reinforcement Learning |
| Issue Date: | 9-Oct-2013 |
| Description: | Gradient-based policy search is an alternative to value-function-based methods for reinforcement learning in non-Markovian domains. One apparent drawback of policy search is its requirement that all actions be 'on-policy'; that is, that there be no explicit exploration. In this paper, we provide a method for using importance sampling to allow any well-behaved directed exploration policy during learning. We show both theoretically and experimentally that using this method can achieve dramatic performance improvements. |
| URI: | http://koha.mediu.edu.my:8181/xmlui/handle/1721 |
| Other Identifiers: | AIM-2001-003 http://hdl.handle.net/1721.1/6076 |
| 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.