Reward-free learning using sparsely-connected hidden Markov models and local controllers.
Kohtaro SabeKenta KawamotoHirotaka SuzukiKatsuki MinaminoKenichi HidaiPublished in: EpiRob (2009)
Keyphrases
- hidden markov models
- reinforcement learning
- sequence classification
- learning algorithm
- speech recognition
- hidden state
- discriminative training
- continuous hidden markov models
- markov models
- conditional random fields
- hierarchical hidden markov model
- sparsely connected
- viterbi algorithm
- latent variable models
- neural network
- social network analysis
- maximum likelihood
- supervised learning
- machine learning