Okada, H. Evolutionary Reinforcement Learning of Binary Neural Network Controllers for Pendulum Task — Part1: Evolution Strategy. Preprints2023, 2023121537. https://doi.org/10.20944/preprints202312.1537.v1
APA Style
Okada, H. (2023). Evolutionary Reinforcement Learning of Binary Neural Network Controllers for Pendulum Task — Part1: Evolution Strategy. Preprints. https://doi.org/10.20944/preprints202312.1537.v1
Chicago/Turabian Style
Okada, H. 2023 "Evolutionary Reinforcement Learning of Binary Neural Network Controllers for Pendulum Task — Part1: Evolution Strategy" Preprints. https://doi.org/10.20944/preprints202312.1537.v1
Abstract
The author previously reported an experimental result of evolutionary reinforcement learning of neural network controllers for the pendulum task. In the previous work, a conventional multilayer perceptron was employed in which connection weights were real numbers. In this study, the author experimentally applies an evolutionary algorithm to the reinforcement training of binary neural networks. In both studies, the same task and the same evolutionary algorithm are utilized, i.e. the pendulum control problem and Evolution Strategy respectively. The only differences lie in the memory size per connection weight and the model size of the neural network. The findings from this study are (1) the performance of the binary MLP with 32 hidden units was inferior to that of the real-valued MLP with 16 hidden units; however, this difference was not statistically significant (p >.05); (2) the trained binary MLP successfully swung the pendulum swiftly into an inverted position and maintained its stability after inversion, as the real-valued MLP had done; and (3) the memory size required to record the binary MLP with 32 hidden units is 3.1% or 6.2% of the memory size required to record the real-valued MLP with 16 hidden units.
Computer Science and Mathematics, Artificial Intelligence and Machine Learning
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.