A Novel Policy for Pre-trained Deep Reinforcement Learning for Speech Emotion Recognition.
Thejan RajapaksheRajib RanaSara KhalifaJiajun LiuBjörn W. SchullerPublished in: ACSW (2022)
Keyphrases
- pre trained
- speech emotion recognition
- reinforcement learning
- optimal policy
- policy search
- markov decision process
- action selection
- training data
- action space
- training examples
- state space
- markov decision processes
- policy gradient
- reward function
- function approximation
- function approximators
- reinforcement learning algorithms
- dynamic programming
- learning algorithm
- machine learning
- control signals
- neural network
- decision trees
- supervised learning
- probabilistic model
- active learning
- appearance variations
- learning process
- computer vision