Characterization of Modeling Errors Affecting Performances of a Robotics Deep Reinforcement Learning Controller in a Sim-to-Real Transfer.
Erica SalvatoGianfranco FenuEric MedvetFelice Andrea PellegrinoPublished in: MIPRO (2021)
Keyphrases
- reinforcement learning
- artificial intelligence
- real time
- transfer learning
- optimal control
- real robot
- neural network
- robot control
- function approximation
- control strategy
- machine learning
- supervised learning
- least squares
- closed loop
- fuzzy logic
- robotic systems
- multi agent
- computer vision
- fuzzy controller
- temporal difference
- real world