Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model.
Alex X. LeeAnusha NagabandiPieter AbbeelSergey LevinePublished in: NeurIPS (2020)
Keyphrases
- actor critic
- latent variable models
- reinforcement learning
- latent variables
- temporal difference
- learning problems
- optimal control
- policy gradient
- reinforcement learning algorithms
- approximate dynamic programming
- neuro fuzzy
- real valued
- function approximation
- policy iteration
- gradient method
- latent space
- latent dirichlet allocation
- monte carlo
- rl algorithms
- hidden markov models
- hidden variables
- probabilistic model
- state space
- random variables
- markov decision processes
- learning algorithm
- markov decision process
- model free
- linear program
- prior knowledge
- dynamical systems
- reinforcement learning methods
- transfer learning
- topic models
- probability distribution
- gaussian process
- posterior distribution
- dynamic programming