Q-learning as well as other learning paradigms depend strongly on the representation of the underlying state space. As a special case of the hidden state problem we investigate the effect of a self-organizing discretization of the state space in a simple control problem. We apply the neural gas algorithm with adaptation of learning rate and neighborhood range to a simulated cart-pole problem. The learning parameters are determined by the ambiguity of successful actions inside each cell.
Identifer | oai:union.ndltd.org:DRESDEN/oai:qucosa:de:qucosa:32942 |
Date | 01 February 2019 |
Creators | Herrmann, Michael, Der, Ralf |
Source Sets | Hochschulschriftenserver (HSSS) der SLUB Dresden |
Language | English |
Detected Language | English |
Type | info:eu-repo/semantics/publishedVersion, doc-type:conferenceObject, info:eu-repo/semantics/conferenceObject, doc-type:Text |
Rights | info:eu-repo/semantics/openAccess |
Relation | 2-910085-18-X |
Page generated in 0.0018 seconds