Loading...
Please wait, while we are loading the content...
Online Feature Learning for Reinforcement Learning Online Feature Learning for Reinforcement Learning (2014)
| Content Provider | CiteSeerX |
|---|---|
| Author | Darmstadt, Laux Darmstadt, Melvin Laux Einreichung, Tag Der |
| Abstract | Hiermit versichere ich, die vorliegende Bachelor-Thesis ohne Hilfe Dritter nur mit den angegebenen Quellen und Hilfsmitteln angefertigt zu haben. Alle Stellen, die aus Quellen entnommen wurden, sind als solche kenntlich gemacht. Diese Arbeit hat in gleicher oder ähnlicher Form noch keiner Prüfungs-behörde vorgelegen. Darmstadt, den 10. Oktober 2014 (Melvin Laux) High Dimensional Reinforcement Learning requires a useful low dimensional representation of the input data to be able to train an agent. However, learning these features requires complete knowledge about the input data, which in general is not available. Initially, to acquire the needed knowledge, many experiments have to be used to explore the input data space at the before training. Preferably, the process of learning useful features should be done on the fly, during the training of the agent. One major challenge for this online feature learning is to find a feature learning method, that is time-efficient and able to adapt to changing input data distributions. One method that meets both of these criteria are incremental autoencoders. In this thesis, we evaluate the perormance of incremental autoencoders for online feature learning for Q-Learning and present limited results of applying incremental autoencoders as feature learning method on the visual pole balancing task. Zusammenfassung |
| File Format | |
| Publisher Date | 2014-01-01 |
| Access Restriction | Open |
| Content Type | Text |
