Continual Reinforcement Learning for Quadruped Robot Locomotion

Continual Reinforcement Learning for Quadruped Robot Locomotion

The ability to learn continuously is crucial for a robot to achieve a high level of intelligence and autonomy. In this paper, we consider continual reinforcement learning (RL) for quadruped robots, which includes the ability to continuously learn sub-sequential tasks (plasticity) and maintain perfor...

Full description

Bibliographic Details
Main Authors: Sibo Gai, Shangke Lyu, Hongyin Zhang, Donglin Wang
Format: Article
Language:English
Published: MDPI AG 2024-01-01
Series:Entropy
Subjects:
continual learning
quadruped robot locomotion
reinforcement learning
plasticity
entropy
Online Access:https://www.mdpi.com/1099-4300/26/1/93

Internet

https://www.mdpi.com/1099-4300/26/1/93

Similar Items