Exploring the Effect of Autoencoder Based Feature Learning for a Deep Reinforcement Learning Policy for Providing Proactive Help.
Nazia AlamBehrooz MostafaviMin ChiTiffany BarnesPublished in: AIED (Posters/Late Breaking Results/...) (2023)
Keyphrases
- reinforcement learning
- learning algorithm
- learning process
- learning tasks
- machine learning
- unsupervised learning
- optimal policy
- learning systems
- deep architectures
- action selection
- deep learning
- policy search
- policy gradient methods
- partially observable environments
- online learning
- artificial neural networks
- function approximation
- partially observable
- model free
- eligibility traces
- reinforcement learning problems
- learning agents
- prior knowledge
- graphical models
- probabilistic model
- active learning