Reinforcement Learning for Quadruped Locomotion.
Kangqiao ZhaoFeng LinHock Soon SeahPublished in: CGI (2021)
Keyphrases
- reinforcement learning
- quadruped robot
- legged robots
- robot control
- function approximation
- real robot
- state space
- mobile robot
- optimal policy
- markov decision processes
- robotic systems
- degrees of freedom
- learning algorithm
- rough terrain
- temporal difference
- dynamic programming
- database
- adaptive control
- reinforcement learning algorithms
- optimal control
- reinforcement learning methods
- autonomous learning
- action space
- reward function
- model free
- learning classifier systems
- autonomous robots
- learning problems
- learning process
- multi agent
- genetic algorithm
- data sets