SD-PDMD: Deep Reinforcement Learning for Robotic Trajectory Imitation.
Yue LiJiexin XieYang LiShijie GuoPublished in: ICTAI (2022)
Keyphrases
- reinforcement learning
- imitation learning
- function approximation
- real robot
- perception action
- state space
- mobile robot
- real time
- robot control
- learning algorithm
- robot motion
- trajectory data
- model free
- reinforcement learning algorithms
- supervised learning
- object manipulation
- learning problems
- markov decision processes
- function approximators
- learning process
- action selection
- temporal difference
- action space
- video sequences
- transition model
- multi agent