40 citations · 119 across the 19 of their papers we have counts for
20 papers
Fast Non-Episodic Adaptive Tuning of Robot Controllers with Online Policy Optimization
James A. Preiss, Fengze Xie, Yiheng Lin +2
We study online algorithms to tune the parameters of a robot controller in a setting where the dynamics, policy class, and optimality objective are all time-varying. The system fol…
Maximizing the Value of Predictions in Control: Accuracy Is Not Enough
Yiheng Lin, Christopher Yeh, Zaiwei Chen +1
We study the value of stochastic predictions in online optimal control with random disturbances. Prior work provides performance guarantees based on prediction error but ignores th…
Approximate Global Convergence of Independent Learning in Multi-Agent Systems
Ruiyang Jin, Zaiwei Chen, Yiheng Lin +2
Independent learning (IL), despite being a popular approach in practice to achieve scalability in large-scale multi-agent systems, usually lacks global convergence guarantees. In t…
Online Policy Optimization in Unknown Nonlinear Systems
Yiheng Lin, James A. Preiss, Fengze Xie +4
We study online policy optimization in nonlinear time-varying dynamical systems where the true dynamical models are unknown to the controller. This problem is challenging because,…
Characterizing Controllability and Observability for Systems with Locality, Communication, and Actuation Constraints
Lauren Conger, Yiheng Lin, Adam Wierman +1
This paper presents a closed-form notion of controllability and observability for systems with communication delays, actuation delays, and locality constraints. The formulation red…
Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions
Tongxin Li, Yiheng Lin, Shaolei Ren +1
We study the tradeoff between consistency and robustness in the context of a single-trajectory time-varying Markov Decision Process (MDP) with untrusted machine-learned advice. Our…
Convergence Rates for Localized Actor-Critic in Networked Markov Potential Games
Zhaoyi Zhou, Zaiwei Chen, Yiheng Lin +1
We introduce a class of networked Markov potential games in which agents are associated with nodes in a network. Each agent has its own local potential function, and the reward of…
Online switching control with stability and regret guarantees
Yingying Li, James A. Preiss, Na Li +3
This paper considers online switching control with a finite candidate controller pool, an unknown dynamical system, and unknown cost functions. The candidate controllers can be uns…
Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning
Yizhou Zhang, Guannan Qu, Pan Xu +3
We study a multi-agent reinforcement learning (MARL) problem where the agents interact over a given network. The goal of the agents is to cooperatively maximize the average of thei…
Bounded-Regret MPC via Perturbation Analysis: Prediction Error, Constraints, and Nonlinearity
Yiheng Lin, Yang Hu, Guannan Qu +2
We study Model Predictive Control (MPC) and propose a general analysis pipeline to bound its dynamic regret. The pipeline first requires deriving a perturbation bound for a finite-…
Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations
Yiheng Lin, James A. Preiss, Emile Anand +3
We study online adaptive policy selection in systems with time-varying costs and dynamics. We develop the Gradient-based Adaptive Policy Selection (GAPS) algorithm together with a…
Decentralized Online Convex Optimization in Networked Systems
Yiheng Lin, Judy Gan, Guannan Qu +2
We study the problem of networked online convex optimization, where each agent individually decides on an action at every time step and agents cooperatively seek to minimize the to…
Equipping Black-Box Policies with Model-Based Advice for Stable Nonlinear Control
Tongxin Li, Ruixiao Yang, Guannan Qu +3
Machine-learned black-box policies are ubiquitous for nonlinear control problems. Meanwhile, crude model information is often available for these problems from, e.g., linear approx…
Online Optimization with Feedback Delay and Nonlinear Switching Cost
Weici Pan, Guanya Shi, Yiheng Lin +1
We study a variant of online optimization in which the learner receives -round about hitting cost and there is a multi-step nonlinear switching cost,…
Perturbation-based Regret Analysis of Predictive Control in Linear Time Varying Systems
Yiheng Lin, Yang Hu, Haoyuan Sun +3
We study predictive control in a setting where the dynamics are time-varying and linear, and the costs are time-varying and well-conditioned. At each time step, the controller rece…
Scalable Multi-Agent Reinforcement Learning for Networked Systems with Average Reward
Guannan Qu, Yiheng Lin, Adam Wierman +1
It has long been recognized that multi-agent reinforcement learning (MARL) faces significant scalability issues due to the fact that the size of the state and action spaces are exp…
Multi-Agent Reinforcement Learning in Stochastic Networked Systems
Yiheng Lin, Guannan Qu, Longbo Huang +1
We study multi-agent reinforcement learning (MARL) in a stochastic network of agents. The objective is to find localized policies that maximize the (discounted) global reward. In g…
Online Optimization with Memory and Competitive Control
Guanya Shi, Yiheng Lin, Soon-Jo Chung +2
This paper presents competitive algorithms for a novel class of online optimization problems with memory. We consider a setting where the learner seeks to minimize the sum of a hit…
Online Optimization with Predictions and Non-convex Losses
Yiheng Lin, Gautam Goel, Adam Wierman
We study online optimization in a setting where an online learner seeks to optimize a per-round hitting cost, which may be non-convex, while incurring a movement cost when changing…
Beyond Online Balanced Descent: An Optimal Algorithm for Smoothed Online Optimization
Gautam Goel, Yiheng Lin, Haoyuan Sun +1
We study online convex optimization in a setting where the learner seeks to minimize the sum of a per-round hitting cost and a movement cost which is incurred when changing decisio…