Model-Based Deep Reinforcement Learning for High-Dimensional Problems, a Survey.
Aske PlaatWalter A. KostersMike PreussPublished in: CoRR (2020)
Keyphrases
- high dimensional problems
- reinforcement learning
- model free
- dimension reduction
- high dimensional
- function approximation
- reinforcement learning algorithms
- deep learning
- temporal difference
- state space
- optimal policy
- learning algorithm
- learning process
- unsupervised learning
- least squares
- image sequences
- image processing
- computer vision
- real world
- policy gradient
- policy search
- robotic control