Picture for Daoyi Dong

Daoyi Dong

Online Planning of Power Flows for Power Systems Against Bushfires Using Spatial Context

Add code
Apr 20, 2024
Viaarxiv icon

Learning Informative Latent Representation for Quantum State Tomography

Add code
Sep 30, 2023
Viaarxiv icon

Attention-Based Transformer Networks for Quantum State Tomography

Add code
May 09, 2023
Viaarxiv icon

Auxiliary Task-based Deep Reinforcement Learning for Quantum Control

Add code
Feb 28, 2023
Viaarxiv icon

A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning

Add code
May 22, 2022
Figure 1 for A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
Figure 2 for A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
Figure 3 for A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
Figure 4 for A Dirichlet Process Mixture of Robust Task Models for Scalable Lifelong Reinforcement Learning
Viaarxiv icon

Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning

Add code
Apr 19, 2022
Figure 1 for Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning
Figure 2 for Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning
Figure 3 for Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning
Figure 4 for Efficient Bayesian Policy Reuse with a Scalable Observation Model in Deep Reinforcement Learning
Viaarxiv icon

Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation

Add code
Mar 06, 2022
Figure 1 for Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation
Figure 2 for Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation
Figure 3 for Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation
Figure 4 for Depthwise Convolution for Multi-Agent Communication with Enhanced Mean-Field Approximation
Viaarxiv icon

Path Planning for Cellular-Connected UAV: A DRL Solution with Quantum-Inspired Experience Replay

Add code
Aug 30, 2021
Figure 1 for Path Planning for Cellular-Connected UAV: A DRL Solution with Quantum-Inspired Experience Replay
Figure 2 for Path Planning for Cellular-Connected UAV: A DRL Solution with Quantum-Inspired Experience Replay
Figure 3 for Path Planning for Cellular-Connected UAV: A DRL Solution with Quantum-Inspired Experience Replay
Figure 4 for Path Planning for Cellular-Connected UAV: A DRL Solution with Quantum-Inspired Experience Replay
Viaarxiv icon

Residual Tensor Train: a Flexible and Efficient Approach for Learning Multiple Multilinear Correlations

Add code
Aug 19, 2021
Figure 1 for Residual Tensor Train: a Flexible and Efficient Approach for Learning Multiple Multilinear Correlations
Figure 2 for Residual Tensor Train: a Flexible and Efficient Approach for Learning Multiple Multilinear Correlations
Figure 3 for Residual Tensor Train: a Flexible and Efficient Approach for Learning Multiple Multilinear Correlations
Figure 4 for Residual Tensor Train: a Flexible and Efficient Approach for Learning Multiple Multilinear Correlations
Viaarxiv icon

Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction

Add code
Apr 15, 2021
Figure 1 for Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction
Figure 2 for Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction
Figure 3 for Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction
Figure 4 for Rule-Based Reinforcement Learning for Efficient Robot Navigation with Space Reduction
Viaarxiv icon