Yung Yi
YOU?
Author Swipe
View article: Curiosity-Driven Multi-Agent Exploration with Mixed Objectives
Curiosity-Driven Multi-Agent Exploration with Mixed Objectives Open
Intrinsic rewards have been increasingly used to mitigate the sparse reward problem in single-agent reinforcement learning. These intrinsic rewards encourage the agent to look for novel experiences, guiding the agent to explore the environ…
View article: Information Source Finding in Networks: Querying with Budgets
Information Source Finding in Networks: Querying with Budgets Open
In this paper, we study a problem of detecting the source of diffused information by querying individuals, given a sample snapshot of the information diffusion graph, where two queries are asked: {\em (i)} whether the respondent is the sou…
View article: QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning
QTRAN++: Improved Value Transformation for Cooperative Multi-Agent Reinforcement Learning Open
QTRAN is a multi-agent reinforcement learning (MARL) algorithm capable of learning the largest class of joint-action value functions up to date. However, despite its strong theoretical guarantee, it has shown poor empirical performance in …
View article: Detection of Atrial Fibrillation Using a Ring-Type Wearable Device (CardioTracker) and Deep Learning Analysis of Photoplethysmography Signals: Prospective Observational Proof-of-Concept Study
Detection of Atrial Fibrillation Using a Ring-Type Wearable Device (CardioTracker) and Deep Learning Analysis of Photoplethysmography Signals: Prospective Observational Proof-of-Concept Study Open
Background Continuous photoplethysmography (PPG) monitoring with a wearable device may aid the early detection of atrial fibrillation (AF). Objective We aimed to evaluate the diagnostic performance of a ring-type wearable device (CardioTra…
View article: Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation
Enlarging Discriminative Power by Adding an Extra Class in Unsupervised Domain Adaptation Open
In this paper, we study the problem of unsupervised domain adaptation that aims at obtaining a prediction model for the target domain using labeled data from the source domain and unlabeled data from the target domain. There exists an arra…
View article: Detection of Atrial Fibrillation Using a Ring-Type Wearable Device (CardioTracker) and Deep Learning Analysis of Photoplethysmography Signals: Prospective Observational Proof-of-Concept Study (Preprint)
Detection of Atrial Fibrillation Using a Ring-Type Wearable Device (CardioTracker) and Deep Learning Analysis of Photoplethysmography Signals: Prospective Observational Proof-of-Concept Study (Preprint) Open
BACKGROUND Continuous photoplethysmography (PPG) monitoring with a wearable device may aid the early detection of atrial fibrillation (AF). OBJECTIVE We aimed to evaluate the diagnostic performance of a ring-type wearable device (Cardio…
View article: Solving Continual Combinatorial Selection via Deep Reinforcement Learning
Solving Continual Combinatorial Selection via Deep Reinforcement Learning Open
We consider the Markov Decision Process (MDP) of selecting a subset of items at each step, termed the Select-MDP (S-MDP). The large state and action spaces of S-MDPs make them intractable to solve with typical reinforcement learning (RL) a…
View article: QTRAN: Learning to Factorize with Transformation for Cooperative\n Multi-Agent Reinforcement Learning
QTRAN: Learning to Factorize with Transformation for Cooperative\n Multi-Agent Reinforcement Learning Open
We explore value-based solutions for multi-agent reinforcement learning\n(MARL) tasks in the centralized training with decentralized execution (CTDE)\nregime popularized recently. However, VDN and QMIX are representative examples\nthat use…
View article: QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning
QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learning Open
We explore value-based solutions for multi-agent reinforcement learning (MARL) tasks in the centralized training with decentralized execution (CTDE) regime popularized recently. However, VDN and QMIX are representative examples that use th…
View article: Deep Learning Approaches to Detect Atrial Fibrillation Using Photoplethysmographic Signals: Algorithms Development Study
Deep Learning Approaches to Detect Atrial Fibrillation Using Photoplethysmographic Signals: Algorithms Development Study Open
BackgroundWearable devices have evolved as screening tools for atrial fibrillation (AF). A photoplethysmographic (PPG) AF detection algorithm was developed and applied to a convenient smartphone-based device with good accuracy. However, pa…
View article: Information source localization with protector diffusion in networks
Information source localization with protector diffusion in networks Open
Recently, the problem of detecting the information source in a network has been much studied, where it has been shown that the detection probability cannot be beyond 31% even for regular trees if the number of infected nodes is sufficientl…
View article: Learning to Schedule Communication in Multi-agent Reinforcement Learning
Learning to Schedule Communication in Multi-agent Reinforcement Learning Open
Many real-world reinforcement learning tasks require multiple agents to make sequential decisions under the agents' interaction, where well-coordinated actions among the agents are crucial to achieve the target goal better at these tasks. …
View article: Joint Optimization of Message Transmissions With Adaptive Selection of CCH Interval in VANETs
Joint Optimization of Message Transmissions With Adaptive Selection of CCH Interval in VANETs Open
In vehicular networks, the safety-related messages (emergency and periodic messages) and non-safety message (RFS: request for service message) should share the scarce wireless resource. Emergency messages deliver time-critical information …
View article: Deep Learning Approaches to Detect Atrial Fibrillation Using Photoplethysmographic Signals: Algorithms Development Study (Preprint)
Deep Learning Approaches to Detect Atrial Fibrillation Using Photoplethysmographic Signals: Algorithms Development Study (Preprint) Open
BACKGROUND Wearable devices have evolved as screening tools for atrial fibrillation (AF). A photoplethysmographic (PPG) AF detection algorithm was developed and applied to a convenient smartphone-based device with good accuracy. However, …
View article: Simulation-based Distributed Coordination Maximization over Networks
Simulation-based Distributed Coordination Maximization over Networks Open
In various online/offline multi-agent networked environments, it is very popular that the system can benefit from coordinating actions of two interacting agents at some cost of coordination. In this paper, we first formulate an optimizatio…
View article: Necessary and Sufficient Budgets in Information Source Finding with Querying: Adaptivity Gap
Necessary and Sufficient Budgets in Information Source Finding with Querying: Adaptivity Gap Open
In this paper, we study a problem of detecting the source of diffused information by querying individuals, given a sample snapshot of the information diffusion graph, where two queries are asked: {\em (i)} whether the respondent is the sou…
View article: Learning Data Dependency with Communication Cost
Learning Data Dependency with Communication Cost Open
In this paper, we consider the problem of recovering a graph that represents the statistical data dependency among nodes for a set of data samples generated by nodes, which provides the basic structure to perform an inference task, such as…
View article: Power of Bonus in Pricing for Crowdsourcing
Power of Bonus in Pricing for Crowdsourcing Open
We consider a simple form of pricing for a crowdsourcing system, where pricing policy is published a priori, and workers then decide their task acceptance. Such a pricing form is widely adopted in practice for its simplicity, e.g., Amazon …
View article: Rumor Source Detection under Querying with Untruthful Answers
Rumor Source Detection under Querying with Untruthful Answers Open
Social networks are the major routes for most individuals to exchange their opinions about new products, social trends and political issues via their interactions. It is often of significant importance to figure out who initially diffuses …
View article: Iterative Bayesian Learning for Crowdsourced Regression
Iterative Bayesian Learning for Crowdsourced Regression Open
Crowdsourcing platforms emerged as popular venues for purchasing human intelligence at low cost for large volume of tasks. As many low-paid workers are prone to give noisy answers, a common practice is to add redundancy by assigning multip…
View article: Adiabatic Persistent Contrastive Divergence Learning
Adiabatic Persistent Contrastive Divergence Learning Open
This paper studies the problem of parameter learning in probabilistic graphical models having latent variables, where the standard approach is the expectation maximization algorithm alternating expectation (E) and maximization (M) steps. H…
View article: Optimal Inference in Crowdsourced Classification via Belief Propagation
Optimal Inference in Crowdsourced Classification via Belief Propagation Open
Crowdsourcing systems are popular for solving large-scale labelling tasks with low-paid workers. We study the problem of recovering the true labels from the possibly erroneous crowdsourced labels under the popular Dawid-Skene model. To add…
View article: Optimality of Belief Propagation for Crowdsourced Classification
Optimality of Belief Propagation for Crowdsourced Classification Open
Crowdsourcing systems are popular for solving large-scale labelling tasks with low-paid (or even non-paid) workers. We study the problem of recovering the true labels from noisy crowdsourced labels under the popular Dawid-Skene model. To a…
View article: Architecture of Protection a Control System Based on Energy Router
Architecture of Protection a Control System Based on Energy Router Open
The Energy Router based on Solid State Transformer will be wildly used in future smart grid to meet requirements of huge distributed generation and bidirectional power flow. Based on principle study of Energy Internet & Energy Router, this…