Personalization of Hearing Aid Compression by Human-in-the-Loop Deep Reinforcement Learning.
Nasim AlamdariEdward LobarinasNasser KehtarnavazPublished in: IEEE Access (2020)
Keyphrases
- reinforcement learning
- human beings
- function approximation
- data compression
- image compression
- compression ratio
- compression scheme
- human subjects
- human computer interaction
- learning process
- markov decision processes
- human experts
- image processing
- optimal policy
- state space
- optimal control
- recommender systems
- human users
- user modeling
- human operators
- policy search