Robust Feedback Motion Policy Design Using Reinforcement Learning on a 3D Digit Bipedal Robot.
Guillermo A. CastilloBowen WengWei ZhangAyonga HereidPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- humanoid robot
- optimal policy
- markov decision processes
- robot motion
- mobile robot
- motion planning
- machine learning
- motion control
- position and orientation
- autonomous robots
- path planning
- robotic systems
- walking speed
- policy search
- function approximation
- design process
- vision system
- state space
- dynamic programming
- image sequences
- learning algorithm