Hidden Markov Model Estimation-Based Q-learning for Partially Observable Markov Decision Process.
Hyung-Jin YoonDonghwan LeeNaira HovakimyanPublished in: CoRR (2018)
Keyphrases
- hidden markov models
- partially observable markov decision process
- state space
- reinforcement learning
- speech recognition
- multi agent
- kernel density
- markov models
- markov model
- learning algorithm
- function approximation
- hidden states
- decision theoretic
- partially observable
- continuous hidden markov models
- optimal policy
- markov chain
- state transition
- single agent
- search algorithm