Implicit Posterior Sampling Reinforcement Learning for Continuous Control.
Shaochen WangBin LiPublished in: ICONIP (2) (2020)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- control system
- control strategies
- control policy
- action space
- transfer learning
- robot control
- real time
- action selection
- learning process
- autonomous robots
- continuous state and action spaces
- continuous state spaces
- sampled data
- function approximation
- monte carlo
- sample size
- probability distribution
- probabilistic model
- dynamic programming