Learning a Faster Locomotion Gait for a Quadruped Robot with Model-Free Deep Reinforcement Learning.
Biao HuShibo ShaoZhengcai CaoQing XiaoQunzhi LiChao MaPublished in: ROBIO (2019)
Keyphrases
- reinforcement learning
- model free
- quadruped robot
- learning process
- learning algorithm
- function approximation
- learning problems
- robot control
- reinforcement learning methods
- reinforcement learning algorithms
- rl algorithms
- state space
- supervised learning
- policy evaluation
- temporal difference learning
- machine learning
- imitation learning
- legged robots
- function approximators
- temporal difference
- action selection
- autonomous robots
- markov decision processes