Reinforcement learning in robotic motion planning by combined experience-based planning and self-imitation learning.
Sha LuoLambert SchomakerPublished in: Robotics Auton. Syst. (2023)
Keyphrases
- motion planning
- imitation learning
- humanoid robot
- reinforcement learning
- robotic tasks
- robotic arm
- trajectory planning
- manipulation tasks
- real robot
- mobile robot
- degrees of freedom
- biologically inspired
- multi modal
- function approximation
- path planning
- state space
- control law
- model free
- reinforcement learning methods
- reinforcement learning algorithms
- collision free
- robotic systems
- multi robot
- control system
- climbing robot
- action selection
- partially observable markov decision processes
- function approximators
- control problems
- temporal difference
- human motion
- markov decision processes
- computer vision
- machine learning
- real time