Applying interpolation-constrained autoencoders to world models approach reinforcement learning
World Models Approach Reinforcement Learning helps to tackle complex problems by breaking down the learning task to Vision Model, Memory Model, and Controller Model. Variational Autoencoder (VAE) is commonly used for Vision Model. However, there has been development of other variants of Autoencoders...
Main Author: | Kevin Winata |
---|---|
Other Authors: | Zinovi Rabinovich |
Format: | Final Year Project (FYP) |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/148004 |
Similar Items
-
Deep reinforcement learning for real world problems
by: Wee, Andrew Chin Ho
Published: (2022) -
Basis set approach in the constrained interpolation profile method /
by: Utsumi, T., et al.
Published: (2003) -
Autoencoding evolutionary search with learning across heterogeneous problems
by: Feng, Liang, et al.
Published: (2021) -
Supervised representation learning with double encoding-layer autoencoder for transfer learning
by: Zhuang, Fuzhen, et al.
Published: (2020) -
Unsupervised word translation with adversarial autoencoder
by: Mohiuddin, Tasnim, et al.
Published: (2021)