no code implementations • 24 May 2023 • Wenjian Hao, Zehui Lu, Zihao Liang, Tianyu Zhou, Shaoshuai Mou
This paper develops a policy learning method for tuning a pre-trained policy to adapt to additional tasks without altering the original task.
no code implementations • 24 May 2023 • Wenjian Hao, Paulo C. Heredia, Bowen Huang, Zehui Lu, Zihao Liang, Shaoshuai Mou
This paper proposes a policy learning algorithm based on the Koopman operator theory and policy gradient approach, which seeks to approximate an unknown dynamical system and search for optimal policy simultaneously, using the observations gathered through interaction with the environment.
no code implementations • 31 Mar 2023 • Zihao Liang, Wenjian Hao, Shaoshuai Mou
By assuming the objective function to be learned is parameterized as a linear combination of features with unknown weights, the proposed approach for IOC is able to achieve a Koopman representation of the unknown dynamics and the unknown weights in objective function together.
no code implementations • 3 Aug 2022 • Benyuan Sun, Jin Dai, Zihao Liang, Congying Liu, Yi Yang, Bo Bai
SIMT lays the foundation of pre-training with large-scale multi-task multi-domain datasets and is proved essential for stable training in our GPPF experiments.
no code implementations • 28 Oct 2020 • Wanxin Jin, Zihao Liang, Shaoshuai Mou
This paper proposes an inverse optimal control method which enables a robot to incrementally learn a control objective function from a collection of trajectory segments.
Robotics