Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model.
Alex X. LeeAnusha NagabandiPieter AbbeelSergey LevinePublished in: CoRR (2019)
Keyphrases
- actor critic
- latent variable models
- reinforcement learning
- latent variables
- temporal difference
- policy gradient
- reinforcement learning algorithms
- optimal control
- approximate dynamic programming
- learning problems
- function approximation
- neuro fuzzy
- probabilistic model
- gradient method
- monte carlo
- real valued
- latent space
- policy iteration
- hidden variables
- markov decision processes
- optimal policy
- average reward
- latent dirichlet allocation
- model free
- state space
- reinforcement learning methods
- supervised learning
- multi agent
- learning algorithm
- hidden markov models
- function approximators
- action selection
- dynamical systems
- random variables
- topic models
- single agent
- posterior distribution
- rl algorithms
- prior knowledge