Multi-Fidelity Reinforcement Learning with Control Variates.
Sami KhairyPrasanna BalaprakashPublished in: ESANN (2023)
Keyphrases
- reinforcement learning
- control problems
- optimal control
- robot control
- learning algorithm
- information systems
- control system
- adaptive control
- control method
- control policy
- reinforcement learning algorithms
- function approximation
- visual quality
- model free
- markov decision processes
- action selection
- transfer learning
- sufficient conditions
- dynamic programming
- markov decision process
- control theory
- artificial neural networks
- temporal difference learning
- robotic control