Reuse Non-Terrain Policies for Learning Terrain-Adaptive Humanoid Locomotion Skills.
Hao YuYuchen LiangYuehu LiuChi ZhangPublished in: ICIP (2023)
Keyphrases
- learning algorithm
- three dimensional
- learning process
- reinforcement learning
- multiresolution
- learning systems
- learning objects
- mobile robot
- lifelong learning
- knowledge acquisition
- online learning
- supervised learning
- associative learning
- neural network
- terrain modeling
- rough terrain
- robot control
- subject matter
- robotic systems
- learning tasks
- dynamic programming
- machine learning