Robust biped locomotion using deep reinforcement learning on top of an analytical control approach.
Mohammadreza KasaeiMiguel AbreuNuno LauArtur PereiraLuís Paulo ReisPublished in: Robotics Auton. Syst. (2021)
Keyphrases
- reinforcement learning
- robot control
- control strategy
- control problems
- optimal control
- control parameters
- control strategies
- control system
- mobile robot
- control method
- robotic systems
- function approximation
- biped robot
- machine learning
- robust stability
- markov decision processes
- computationally efficient
- state space
- learning algorithm
- humanoid robot
- optimal policy
- adaptive control
- dynamic environments
- learning process