Zhaolin Ren
YOU?
Author Swipe
View article: Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations
Offline Imitation Learning upon Arbitrary Demonstrations by Pre-Training Dynamics Representations Open
Limited data has become a major bottleneck in scaling up offline imitation learning (IL). In this paper, we propose enhancing IL performance under limited expert data by introducing a pre-training stage that learns dynamics representations…
View article: Regression-Based Single-Point Zeroth-Order Optimization
Regression-Based Single-Point Zeroth-Order Optimization Open
Zeroth-order optimization (ZO) is widely used for solving black-box optimization and control problems. In particular, single-point ZO (SZO) is well-suited to online or dynamic problem settings due to its requirement of only a single functi…
View article: An AI-Cyborg System for Adaptive Intelligent Modulation of Organoid Maturation
An AI-Cyborg System for Adaptive Intelligent Modulation of Organoid Maturation Open
Recent advancements in flexible bioelectronics have enabled continuous, long-term stable interrogation and intervention of biological systems. However, effectively utilizing the interrogated data to modulate biological systems to achieve s…
View article: Scalable spectral representations for multi-agent reinforcement learning in network MDPs
Scalable spectral representations for multi-agent reinforcement learning in network MDPs Open
Network Markov Decision Processes (MDPs), a popular model for multi-agent control, pose a significant challenge to efficient learning due to the exponential growth of the global state-action space with the number of agents. In this work, u…
View article: Distributed Thompson sampling under constrained communication
Distributed Thompson sampling under constrained communication Open
In Bayesian optimization, a black-box function is maximized via the use of a surrogate model. We apply distributed Thompson sampling, using a Gaussian process as a surrogate model, to approach the multi-agent Bayesian optimization problem.…
View article: Enhancing Preference-based Linear Bandits via Human Response Time
Enhancing Preference-based Linear Bandits via Human Response Time Open
Interactive preference learning systems infer human preferences by presenting queries as pairs of options and collecting binary choices. Although binary choices are simple and widely used, they provide limited information about preference …
View article: Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpoint
Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpoint Open
We study sim-to-real skill transfer and discovery in the context of robotics control using representation learning. We draw inspiration from spectral decomposition of Markov decision processes. The spectral decomposition brings about repre…
View article: TS-RSR: A provably efficient approach for batch Bayesian Optimization
TS-RSR: A provably efficient approach for batch Bayesian Optimization Open
This paper presents a new approach for batch Bayesian Optimization (BO) called Thompson Sampling-Regret to Sigma Ratio directed sampling (TS-RSR), where we sample a new batch of actions by minimizing a Thompson Sampling approximation of a …
View article: Research On The Performance Test Method Of Elevator Brake
Research On The Performance Test Method Of Elevator Brake Open
The elevator brake is an important part to ensure the safe operation of the elevator, and its performance directly determines the safety of the whole machine. This paper describes a brake performance test scheme and test principle, and mak…
View article: Explainable multi-task learning for multi-modality biological data analysis
Explainable multi-task learning for multi-modality biological data analysis Open
Current biotechnologies can simultaneously measure multiple high-dimensional modalities (e.g., RNA, DNA accessibility, and protein) from the same cells. A combination of different analytical tasks (e.g., multi-modal integration and cross-m…
View article: Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding
Stochastic Nonlinear Control via Finite-dimensional Spectral Dynamic Embedding Open
This paper proposes an approach, Spectral Dynamics Embedding Control (SDEC), to optimal control for nonlinear stochastic systems. This method reveals an infinite-dimensional feature representation induced by the system's nonlinear stochast…
View article: The Failure Analysis of Unintended Elevator Car Movement Protection
The Failure Analysis of Unintended Elevator Car Movement Protection Open
The unintended movement protection device of elevator car can prevent the accident of passenger shearing and extrusion caused by the fracture of elevator traction wheel shaft and the failure of control system components. However, due to th…
View article: On Controller Reduction in Linear Quadratic Gaussian Control with Performance Bounds
On Controller Reduction in Linear Quadratic Gaussian Control with Performance Bounds Open
The problem of controller reduction has a rich history in control theory. Yet, many questions remain open. In particular, there exist very few results on the order reduction of general non-observer based controllers and the subsequent quan…
View article: Escaping saddle points in zeroth-order optimization: the power of two-point estimators
Escaping saddle points in zeroth-order optimization: the power of two-point estimators Open
Two-point zeroth order methods are important in many applications of zeroth-order optimization, such as robotics, wind farms, power systems, online optimization, and adversarial robustness to black-box attacks in deep neural networks, wher…
View article: FedDAR: Federated Domain-Aware Representation Learning
FedDAR: Federated Domain-Aware Representation Learning Open
Cross-silo Federated learning (FL) has become a promising tool in machine learning applications for healthcare. It allows hospitals/institutions to train models with sufficient data while the data is kept private. To make sure the FL model…
View article: Gradient Play in Stochastic Games: Stationary Points and Local Geometry
Gradient Play in Stochastic Games: Stationary Points and Local Geometry Open
We study the stationary points and local geometry of gradient play for stochastic games (SGs), where each agent tries to maximize its own total discounted reward by making decisions independently based on current state information which is…
View article: Analysis on mechanical characteristics of brake wheel and brake shoe of elevator traction machine
Analysis on mechanical characteristics of brake wheel and brake shoe of elevator traction machine Open
This paper analyzes the change of brake torque during normal stop and emergency braking of elevator. Taking the permanent magnet synchronous elevator traction machine as an example, the mechanical characteristics of the brake wheel and bra…
View article: Gradient play in stochastic games: stationary points, convergence, and sample complexity
Gradient play in stochastic games: stationary points, convergence, and sample complexity Open
We study the performance of the gradient play algorithm for stochastic games (SGs), where each agent tries to maximize its own total discounted reward by making decisions independently based on current state information which is shared bet…
View article: Gradient Play in Multi-Agent Markov Stochastic Games: Stationary Points and Convergence
Gradient Play in Multi-Agent Markov Stochastic Games: Stationary Points and Convergence Open
We study the performance of the gradient play algorithm for multi-agent tabular Markov decision processes (MDPs), which are also known as stochastic games (SGs), where each agent tries to maximize its own total discounted reward by making …
View article: Zeroth-Order Feedback Optimization for Cooperative Multi-Agent Systems
Zeroth-Order Feedback Optimization for Cooperative Multi-Agent Systems Open
We study a class of cooperative multi-agent optimization problems, where each agent is associated with a local action vector and a local cost, and the goal is to cooperatively find the joint action profile that minimizes the average of the…
View article: LQR with Tracking: A Zeroth-order Approach and Its Global Convergence
LQR with Tracking: A Zeroth-order Approach and Its Global Convergence Open
There has been substantial recent progress on the theoretical understanding of model-free approaches to Linear Quadratic Regulator (LQR) problems. Much attention has been devoted to the special case when the goal is to drive the state clos…
View article: Federated LQR: Learning through Sharing.
Federated LQR: Learning through Sharing. Open
In many multi-agent reinforcement learning applications such as flocking, multi-robot applications and smart manufacturing, distinct agents share similar dynamics but face different objectives. In these applications, an important question …
View article: Delay-Adaptive Distributed Stochastic Optimization
Delay-Adaptive Distributed Stochastic Optimization Open
In large-scale optimization problems, distributed asynchronous stochastic gradient descent (DASGD) is a commonly used algorithm. In most applications, there are often a large number of computing nodes asynchronously computing gradient info…