- Title
- A small spiking neural network with LQR control applied to the acrobot
- Creator
- Wiklendt, Luke; Chalup, Stephan; Middleton, Rick
- Relation
- Neural Computing & Applications Vol. 18, Issue 4, p. 369-375
- Publisher Link
- http://dx.doi.org/10.1007/s00521-008-0187-1
- Publisher
- Springer
- Resource Type
- journal article
- Date
- 2009
- Description
- This paper presents the results of a computer simulation which, combined a small network of spiking neurons with linear quadratic regulator (LQR) control to solve the acrobot swing-up and balance task. To our knowledge, this task has not been previously solved with spiking neural networks. Input to the network was drawn from the state of the acrobot, and output was torque, either directly applied to the actuated joint, or via the switching of an LQR controller designed for balance. The neural network’s weights were tuned using a (μ + λ)-evolution strategy without recombination, and neurons’ parameters, were chosen to roughly approximate biological neurons.
- Subject
- spiking neural networks; acrobot; LQR; evolution
- Identifier
- uon:7786
- Identifier
- http://hdl.handle.net/1959.13/808937
- Identifier
- ISSN:0941-0643
- Full Text
- Reviewed
- Hits: 3148
- Visitors: 4114
- Downloads: 400
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | SOURCE1 | Author final version | 629 KB | Adobe Acrobat PDF | View Details Download |