A novel policy for pre-trained Deep Reinforcement Learning for Speech Emotion Recognition.
Thejan RajapaksheRajib RanaSara KhalifaBjörn W. SchullerJiajun LiuPublished in: CoRR (2021)
Keyphrases
- pre trained
- speech emotion recognition
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- training data
- action selection
- function approximators
- policy gradient
- training examples
- state space
- reward function
- function approximation
- markov decision processes
- control signals
- learning algorithm
- reinforcement learning algorithms
- action space
- machine learning
- dynamic programming
- active learning
- semi supervised learning
- supervised learning
- learning process
- decision trees