The Benefits of Model-Based Generalization in Reinforcement Learning.
Kenny YoungAditya RameshLouis KirschJürgen SchmidhuberPublished in: CoRR (2022)
Keyphrases
- reinforcement learning
- model free
- function approximation
- reinforcement learning algorithms
- learning algorithm
- robotic control
- temporal difference
- state space
- optimal control
- dynamic programming
- learning process
- cost reduction
- robot control
- data driven
- supervised learning
- control problems
- reinforcement learning methods
- information retrieval