SYNLOCO: Synthesizing Central Pattern Generator and Reinforcement Learning for Quadruped Locomotion.
Xinyu ZhangZhiyuan XiaoQingrui ZhangWei PanPublished in: CoRR (2023)
Keyphrases
- central pattern generator
- reinforcement learning
- state space
- quadruped robot
- learning algorithm
- reinforcement learning algorithms
- machine learning
- robotic control
- legged robots
- function approximation
- optimal control
- partially observable
- temporal difference learning
- optimal policy
- multi agent
- markov decision processes
- model free
- action selection
- dynamic programming
- learning process
- real robot
- markov decision process
- relational reinforcement learning
- least squares