Search Results for author: Dikai Liu

Found 3 papers, 0 papers with code

Modular Transfer Learning with Transition Mismatch Compensation for Excessive Disturbance Rejection

no code implementations29 Jul 2020 Tianming Wang, Wen-jie Lu, Huan Yu, Dikai Liu

In this paper, we propose a transfer learning framework that adapts a control policy for excessive disturbance rejection of an underwater robot under dynamics model mismatch.

Transfer Reinforcement Learning

A2: Extracting Cyclic Switchings from DOB-nets for Rejecting Excessive Disturbances

no code implementations1 Nov 2019 Wen-jie Lu, Dikai Liu

This paper proposes an Attention-based Abstraction (A${}^2$) approach to extract a finite-state automaton, referred to as a Key Moore Machine Network (KMMN), to capture the switching mechanisms exhibited by the DOB-net in dealing with multiple such POMDPs.

Reinforcement Learning (RL)

DOB-Net: Actively Rejecting Unknown Excessive Time-Varying Disturbances

no code implementations10 Jul 2019 Tianming Wang, Wen-jie Lu, Zheng Yan, Dikai Liu

This paper presents an observer-integrated Reinforcement Learning (RL) approach, called Disturbance OBserver Network (DOB-Net), for robots operating in environments where disturbances are unknown and time-varying, and may frequently exceed robot control capabilities.

Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.