Reinforcement Learning of Speech Recognition System Based on Policy Gradient and Hypothesis Selection.
Taku KatoTakahiro ShinozakiPublished in: ICASSP (2018)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- policy search
- function approximation
- reinforcement learning algorithms
- optimal control
- policy gradient methods
- gradient method
- model free reinforcement learning
- approximation methods
- state space
- optimal policy
- average reward
- reinforcement learning methods
- state action
- machine learning
- multi agent
- variance reduction
- partially observable markov decision processes
- markov decision processes
- temporal difference
- transfer learning
- temporal difference learning
- markov decision process
- dynamic programming
- model free