A recurrent Markov state-space generative model for sequences.
Anand RamachandranSteven S. LumettaEric W. KleeDeming ChenPublished in: AISTATS (2019)
Keyphrases
- learning process
- generative model
- state space
- reinforcement learning
- markov chain
- probabilistic model
- bayesian framework
- posterior probability
- learning environment
- em algorithm
- semi supervised
- hidden markov models
- state variables
- optimal policy
- discriminative learning
- markov decision processes
- topic models
- dynamic programming
- prior knowledge
- conditional random fields
- latent dirichlet allocation
- dynamic textures
- reward function
- search space
- discriminative models
- expectation maximization
- machine learning
- low level
- markov chain monte carlo
- learned models
- dirichlet process mixture models
- fully bayesian