Deep Reinforcement Learning Autoencoder with Noisy Feedback.
Mathieu GoutayFayçal Ait AoudiaJakob HoydisPublished in: WiOpt (2019)
Keyphrases
- reinforcement learning
- learning algorithm
- function approximation
- optimal policy
- reinforcement learning algorithms
- learning process
- real time
- multi agent
- state space
- deep learning
- noisy data
- model free
- sensory inputs
- reinforcement learning methods
- temporal difference learning
- noisy environments
- user feedback
- transfer learning
- unsupervised learning
- relevance feedback
- semi supervised