7 papers
Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twin Construction
Haoting Zhang, Haoxian Chen, Jiayuan Sheng +4
Building a blockchain digital twin largely requires translating domain knowledge and specific system descriptions into a simulator architecture, calibrating its parameters against…
JEPA-Bisim: Learning Robust Visual Representations for Planning with Joint-Embedding Predictive World Models
Leonardo F. Toso, Davit Shadunts, Yunyang Lu +5
World models learned from high-dimensional visual observations allow agents to make decisions and plan directly in latent space, avoiding pixel-level reconstruction. However, recen…
SOCRATES: Simulation Optimization with Correlated Replicas and Adaptive Trajectory Evaluations
Haoting Zhang, Haoxian Chen, Donglin Zhan +5
The field of simulation optimization (SO) encompasses various methods developed to optimize complex, expensive-to-sample stochastic systems. Established methods include, but are no…
Collaborative Bayesian Optimization via Wasserstein Barycenters
Donglin Zhan, Haoting Zhang, Rhonda Righter +2
Motivated by the growing need for black-box optimization and data privacy, we introduce a collaborative Bayesian optimization (BO) framework that addresses both of these challenges…
Coreset-Based Task Selection for Sample-Efficient Meta-Reinforcement Learning
Donglin Zhan, Leonardo F. Toso, James Anderson
We study task selection to enhance sample efficiency in model-agnostic meta-reinforcement learning (MAML-RL). Traditional meta-RL typically assumes that all available tasks are equ…
Data-Efficient and Robust Task Selection for Meta-Learning
Donglin Zhan, James Anderson
Meta-learning methods typically learn tasks under the assumption that all tasks are equally important. However, this assumption is often not valid. In real-world applications, task…
Meta-Learning Linear Quadratic Regulators: A Policy Gradient MAML Approach for Model-free LQR
Leonardo F. Toso, Donglin Zhan, James Anderson +1
We investigate the problem of learning linear quadratic regulators (LQR) in a multi-task, heterogeneous, and model-free setting. We characterize the stability and personalization g…