Personalization of Hearing Aid Compression by Human-In-Loop Deep Reinforcement Learning.
Nasim AlamdariEdward LobarinasNasser KehtarnavazPublished in: CoRR (2020)
Keyphrases
- reinforcement learning
- function approximation
- human beings
- human interaction
- data compression
- compression algorithm
- image compression
- user profiles
- multi agent
- optimal policy
- neural network
- learning algorithm
- machine learning
- reinforcement learning algorithms
- robotic control
- function approximators
- model free
- sign language
- human behavior
- human subjects
- compression ratio
- state space
- data structure
- website