Trajectory-based Reinforcement Learning of Non-prehensile Manipulation Skills for Semi-Autonomous Teleoperation.
Sangbeom ParkYoonbyung ChaiSunghyun ParkJeongeun ParkKyungjae LeeSungjoon ChoiPublished in: CoRR (2021)
Keyphrases
- semi autonomous
- reinforcement learning
- real robot
- dialogue management
- reinforcement learning algorithms
- function approximation
- model free
- state space
- multi agent
- optimal policy
- human operators
- machine learning
- partially observable
- optimal control
- augmented reality
- dynamic programming
- learning process
- temporal difference
- transfer learning
- learning agent