Search Results for author: Zhiyong Chen

Found 16 papers, 0 papers with code

Dynamic Programming-based Approximate Optimal Control for Model-Based Reinforcement Learning

no code implementations22 Dec 2023 Prakash Mallick, Zhiyong Chen

This article proposes an improved trajectory optimization approach for stochastic optimal control of dynamical systems affected by measurement noise by combining optimal control with maximum likelihood techniques to improve the reduction of the cumulative cost-to-go.

Model-based Reinforcement Learning reinforcement-learning

A nonparametric learning framework for nonlinear robust output regulation

no code implementations26 Sep 2023 Shimin Wang, Martin Guay, Zhiyong Chen

An explicit continuous nonlinear mapping was constructed recently in [1] under the assumption that the steady-state generator is linear in the exogenous signal.

Asymptotical Cooperative Cruise Fault Tolerant Control for Multiple High-speed Trains with State Constraints

no code implementations4 Nov 2022 Zhixin Zhang, Zhiyong Chen

Based on the estimated values of states and faults, a distributed fault tolerance controller is designed to realize asymptotical cooperative cruise control of trains under the dual constraints of ensuring both position difference and velocity difference of adjacent trains in specified ranges throughout the whole process.

Position

Boosting Exploration in Actor-Critic Algorithms by Incentivizing Plausible Novel States

no code implementations1 Oct 2022 Chayan Banerjee, Zhiyong Chen, Nasimul Noman

Actor-critic (AC) algorithms are a class of model-free deep reinforcement learning algorithms, which have proven their efficacy in diverse domains, especially in solving continuous control problems.

Continuous Control

Predictive GAN-powered Multi-Objective Optimization for Hybrid Federated Split Learning

no code implementations2 Sep 2022 Benshun Yin, Zhiyong Chen, Meixia Tao

In contrast, split learning (SL) can reduce the computing load of devices by using model splitting and assignment, but increase the communication burden to transmit intermediate results.

Federated Learning Generative Adversarial Network

Coevolutionary Dynamics of Actions and Opinions in Social Networks

no code implementations15 Jun 2022 Hassan Dehghani Aghbolagh, Mengbin Ye, Lorenzo Zino, Ming Cao, Zhiyong Chen

Empirical studies suggest a deep intertwining between opinion formation and decision-making processes, but these have been treated as separate problems in the study of dynamical models for social networks.

Decision Making

Improved Soft Actor-Critic: Mixing Prioritized Off-Policy Samples with On-Policy Experience

no code implementations24 Sep 2021 Chayan Banerjee, Zhiyong Chen, Nasimul Noman

It is comparatively more stable and sample efficient when tested on a number of continuous control tasks in MuJoCo environments.

Continuous Control

Optimal Actor-Critic Policy with Optimized Training Datasets

no code implementations16 Aug 2021 Chayan Banerjee, Zhiyong Chen, Nasimul Noman, Mohsen Zamani

Actor-critic (AC) algorithms are known for their efficacy and high performance in solving reinforcement learning problems, but they also suffer from low sampling efficiency.

IFR: Iterative Fusion Based Recognizer For Low Quality Scene Text Recognition

no code implementations13 Aug 2021 Zhiwei Jia, Shugong Xu, Shiyi Mu, Yue Tao, Shan Cao, Zhiyong Chen

In this paper, we propose an Iterative Fusion based Recognizer (IFR) for low quality scene text recognition, taking advantage of refined text images input and robust feature representation.

Image Restoration Scene Text Recognition

A Symbolic Regression Method for Dynamic Modeling and Control of Quadrotor UAVs

no code implementations7 May 2021 Wei Fang, Zhiyong Chen

This paper presents a mathematic dynamic model of a quadrotor unmanned aerial vehicle (QUAV) by using the symbolic regression approach and then proposes a hierarchical control scheme for trajectory tracking.

Position regression +1

Contrastive Disentanglement in Generative Adversarial Networks

no code implementations5 Mar 2021 Lili Pan, Peijun Tang, Zhiyong Chen, Zenglin Xu

Disentanglement is defined as the problem of learninga representation that can separate the distinct, informativefactors of variations of data.

Contrastive Learning Disentanglement

Adaptive Cooperative Tracking and Parameter Estimation of an Uncertain Leader over General Directed Graphs

no code implementations24 Mar 2020 Shimin Wang, Hongwei Zhang, Zhiyong Chen

Distributed adaptive observers are designed for all follower nodes, simultaneously estimate the state and parameters of the leader node.

A Study on Angular Based Embedding Learning for Text-independent Speaker Verification

no code implementations12 Aug 2019 Zhiyong Chen, Zongze Ren, Shugong Xu

Learning a good speaker embedding is important for many automatic speaker recognition tasks, including verification, identification and diarization.

Speaker Recognition Text-Independent Speaker Verification

Triplet Based Embedding Distance and Similarity Learning for Text-independent Speaker Verification

no code implementations6 Aug 2019 Zongze Ren, Zhiyong Chen, Shugong Xu

The improvements are both based on triplet cause the training stage and the evaluation stage of the baseline x-vector system focus on different aims.

Speaker Recognition Text-Independent Speaker Verification

Event-triggered controllers based on the supremum norm of sampling-induced error

no code implementations14 Jun 2018 Lijun Zhu, Zhiyong Chen, David J. Hill, Shengli Du

Specifically, the closed-loop system is associated with a pair of auxiliary input and output.

Systems and Control

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