Login / Signup
Off-policy adversarial imitation learning for robotic tasks with low-quality demonstrations.
Guoyu Zuo
Qishen Zhao
Kexin Chen
Jiangeng Li
Daoxiong Gong
Published in:
Appl. Soft Comput. (2020)
Keyphrases
</>
low quality
imitation learning
robotic tasks
robotic systems
high quality
motion planning
humanoid robot
mobile robot
vision system
multi robot
multi agent
reinforcement learning
planning under uncertainty
dynamic environments
real time
multi modal
learning algorithm
machine learning