Deep Reinforcement Learning Autoencoder with Noisy Feedback.
Mathieu GoutayFayçal Ait AoudiaJakob HoydisPublished in: CoRR (2018)
Keyphrases
- function approximators
- reinforcement learning
- function approximation
- temporal difference learning
- action space
- reinforcement learning algorithms
- state space
- learning tasks
- noisy environments
- relevance feedback
- model free
- learning algorithm
- noisy data
- markov decision processes
- multi agent
- machine learning
- user feedback
- noise free
- transfer learning
- optimal policy
- artificial neural networks
- multi agent systems
- transition model