University of Central Florida
Innovative Modification in Reinforcement Learning Models Using Recurrent Neural Network and Autoencoder
Abstract
dc:description.abstractThe researchers explored building a generative model with the combination of Variational Autoencoders (VAEs) and Generative Adversarial Network (GAN) to offer better results when the agent interacts with the environment. The premise is that the agent model can train the unsupervised environment and increase the imaging quality. An experiment was performed on car racing based on the designed agent model with features that could effectively be extracted to help produce reliable information. The combination of VAE and GAN provides better feature extraction to gather relevant data and solve the complexity. Another novel approach was performed in which the world model has a modified Recurrent Neural Network (RNN) model and was carried out by a bi-directional gated recurrent unit (BGRU) as opposed to a traditional long short-term memory (LSTM) model. BGRU tends to use less memory while executing and training faster than an LSTM, as it uses fewer training parameters. However, the LSTM model provided greater accuracy with datasets using longer sequences. Based on practical implementation, the BGRU model produced better performance results.
Degree
thesis:*- Grantor dc:publisher
- University of Central Florida
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Almalki, Ali
- Contributors dc:contributor
-
- Wocjan, Pawel
Subjects
dc:subject × 3- Generative models; Variational Autoencoders; Generative Adversarial Networks; Bi-directional Gated Recurrent Unit; Feature extraction
- Computer Sciences
- Reinforcement learning; Neural networks (Computer science)--Models; Automobile driving simulators--Technological innovations; Deep learning (Machine learning); Machine learning--Experiments
Rights
- Language dc:language
- English
Identifiers
dc:identifier.*- Identifier
- CFE0009096; DP0026429