Yi Ouyang

Publication Activity (10 Years)

Years Active: 2012-2024
Publications (10 Years): 45

Top Topics

Reinforcement Learning

Markov Decision Processes

Top Venues

IEEE Trans. Autom. Control.

Publications

Berk Bozkurt, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang
Model approximation in MDPs with unbounded per-step cost. CoRR (2024)
Yi Ouyang, Hamidreza Tavafoghi, Demosthenis Teneketzis
An Approach to Stochastic Dynamic Games with Asymmetric Information and Hidden Actions. CoRR (2023)
Berk Bozkurt, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang
Weighted-Norm Bounds on Model Approximation in MDPs with Unbounded Per-Step Cost. CDC (2023)
Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang
Scalable Regret for Learning to Control Network-Coupled Subsystems With Unknown Dynamics. IEEE Trans. Control. Netw. Syst. 10 (1) (2023)
Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang
A modified Thompson sampling-based learning algorithm for unknown linear systems. CDC (2022)
Yi Ouyang, Demosthenis Teneketzis
Signaling for decentralized routing in a queueing network. Ann. Oper. Res. 317 (2) (2022)
Hamidreza Tavafoghi, Yi Ouyang, Demosthenis Teneketzis
A Unified Approach to Dynamic Decision Problems With Asymmetric Information: Nonstrategic Agents. IEEE Trans. Autom. Control. 67 (3) (2022)
Yi Ouyang, Seyed Mohammad Asghari, Ashutosh Nayyar
Optimal Infinite Horizon Decentralized Networked Controllers With Unreliable Communication. IEEE Trans. Autom. Control. 66 (4) (2021)
Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang
Scalable regret for learning to control network-coupled subsystems with unknown dynamics. CoRR (2021)
Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang
A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems. CoRR (2021)
Huidong Gao, Yi Ouyang, Masayoshi Tomizuka
Online Learning in Planar Pushing with Combined Prediction Model. ACC (2021)
Mukul Gagrani, Yi Ouyang, Mohammad Rasouli, Ashutosh Nayyar
Worst-Case Guarantees for Remote Estimation of an Uncertain Source. IEEE Trans. Autom. Control. 66 (4) (2021)
Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang
Thompson sampling for linear quadratic mean-field teams. CDC (2021)
Mukul Gagrani, Sagar Sudhakara, Aditya Mahajan, Ashutosh Nayyar, Yi Ouyang
Thompson sampling for linear quadratic mean-field teams. CoRR (2020)
Yi Ouyang, Mukul Gagrani, Rahul Jain
Posterior Sampling-Based Reinforcement Learning for Control of Unknown Linear Systems. IEEE Trans. Autom. Control. 65 (8) (2020)
Yi Ouyang, Richard Y. Zhang, Javad Lavaei, Pravin Varaiya
Large-Scale Traffic Signal Offset Optimization. IEEE Trans. Control. Netw. Syst. 7 (3) (2020)
Seyed Mohammad Asghari, Yi Ouyang, Ashutosh Nayyar
Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems. CoRR (2020)
Seyed Mohammad Asghari, Yi Ouyang, Ashutosh Nayyar
Regret Bounds for Decentralized Learning in Cooperative Multi-Agent Dynamical Systems. UAI (2020)
Yi Ouyang, Richard Y. Zhang, Javad Lavaei, Pravin Varaiya
Large-Scale Traffic Signal Offset Optimization. CoRR (2019)
Seyed Mohammad Asghari, Yi Ouyang, Ashutosh Nayyar
Optimal Local and Remote Controllers With Unreliable Uplink Channels. IEEE Trans. Autom. Control. 64 (5) (2019)
Mukul Gagrani, Yi Ouyang, Mohammad Rasouli, Ashutosh Nayyar
Worst-case Guarantees for Remote Estimation of an Uncertain Source. CoRR (2019)
Seyed Mohammad Asghari, Yi Ouyang, Ashutosh Nayyar, Amir Salman Avestimehr
An Approximation Algorithm for Optimal Clique Cover Delivery in Coded Caching. IEEE Trans. Commun. 67 (7) (2019)
Huidong Gao, Yi Ouyang, Masayoshi Tomizuka
Online Learning in Planar Pushing with Combined Prediction Model. CoRR (2019)
Hamidreza Tavafoghi, Yi Ouyang, Demosthenis Teneketzis
A Sufficient Information Approach to Decentralized Decision Making. CDC (2018)
Cédric Josz, Yi Ouyang, Richard Y. Zhang, Javad Lavaei, Somayeh Sojoudi
A theory on the absence of spurious solutions for nonconvex and nonsmooth optimization. NeurIPS (2018)
Seyed Mohammad Asghari, Yi Ouyang, Ashutosh Nayyar
Decentralized Control of Stochastically Switched Linear System with Unreliable Communication. CoRR (2018)
Yi Ouyang, Seyed Mohammad Asghari, Ashutosh Nayyar
Optimal local and remote controllers with unreliable communication: the infinite horizon case. ACC (2018)
Seyed Mohammad Asghari, Yi Ouyang, Ashutosh Nayyar
Decentralized Control of Stochastically Switched Linear System with Unreliable Communication. ACC (2018)
Yi Ouyang, Richard Y. Zhang, Javad Lavaei, Pravin Varaiya
Conic Approximation with Provable Guarantee for Traffic Signal Offset Optimization. CDC (2018)
Yi Ouyang, Seyed Mohammad Asghari, Ashutosh Nayyar
Optimal Infinite Horizon Decentralized Networked Controllers with Unreliable Communication. CoRR (2018)
Seyed Mohammad Asghari, Yi Ouyang, Ashutosh Nayyar, Amir Salman Avestimehr
Optimal Coded Multicast in Cache Networks with Arbitrary Content Placement. ICC (2018)
Hamidreza Tavafoghi, Yi Ouyang, Demosthenis Teneketzis
A Unified Approach to Dynamic Decision Problems with Asymmetric Information - Part II: Strategic Agents. CoRR (2018)
Hamidreza Tavafoghi, Yi Ouyang, Demosthenis Teneketzis
A Unified Approach to Dynamic Decision Problems with Asymmetric Information - Part I: Non-Strategic Agents. CoRR (2018)
Yi Ouyang, Seyed Mohammad Asghari, Ashutosh Nayyar
Stochastic teams with randomized information structures. CDC (2017)
Yi Ouyang, Mukul Gagrani, Ashutosh Nayyar, Rahul Jain
Learning Unknown Markov Decision Processes: A Thompson Sampling Approach. CoRR (2017)
Yi Ouyang, Mukul Gagrani, Ashutosh Nayyar, Rahul Jain
Learning Unknown Markov Decision Processes: A Thompson Sampling Approach. NIPS (2017)
Yi Ouyang, Mukul Gagrani, Rahul Jain
Control of unknown linear systems with Thompson sampling. Allerton (2017)
Yi Ouyang, Mukul Gagrani, Rahul Jain
Learning-based Control of Unknown Linear Systems with Thompson Sampling. CoRR (2017)
Yi Ouyang, Hamidreza Tavafoghi, Demosthenis Teneketzis
Dynamic Games With Asymmetric Information: Common Information Based Perfect Bayesian Equilibria and Sequential Decomposition. IEEE Trans. Autom. Control. 62 (1) (2017)
Seyed Mohammad Asghari, Yi Ouyang, Ashutosh Nayyar, Amir Salman Avestimehr
Optimal Coded Multicast in Cache Networks with Arbitrary Content Placement. CoRR (2017)
Seyed Mohammad Asghari, Yi Ouyang, Ashutosh Nayyar
Optimal Local and Remote Controllers with Unreliable Uplink Channels. CoRR (2016)
Yi Ouyang, Seyed Mohammad Asghari, Ashutosh Nayyar
Optimal local and remote controllers with unreliable communication. CDC (2016)
Yi Ouyang, Seyed Mohammad Asghari, Ashutosh Nayyar
Optimal Local and Remote Controllers with Unreliable Communication. CoRR (2016)
Yi Ouyang, Rahul Jain, Pravin Varaiya
On the existence of near-optimal fixed time control of traffic intersection signals. Allerton (2016)
Hamidreza Tavafoghi, Yi Ouyang, Demosthenis Teneketzis
On stochastic dynamic games with delayed sharing information structure. CDC (2016)
Yang Liu, Yi Ouyang, Mingyan Liu
Optimal Relay Selection with Non-negligible Probing Time. CoRR (2015)
Yi Ouyang, Demosthenis Teneketzis
A Common Information-Based Multiple Access Protocol Achieving Full Throughput and Linear Delay. CoRR (2015)
Yi Ouyang, Hamidreza Tavafoghi, Demosthenis Teneketzis
Dynamic Games with Asymmetric Information: Common Information Based Perfect Bayesian Equilibria and Sequential Decomposition. CoRR (2015)
Yang Liu, Yi Ouyang, Mingyan Liu
Optimal relay selection with non-negligible probing time. ICC (2015)
Yi Ouyang, Hamidreza Tavafoghi, Demosthenis Teneketzis
Dynamic oligopoly games with private Markovian dynamics. CDC (2015)
Yi Ouyang, Demosthenis Teneketzis
A common information-based multiple access protocol achieving full throughput. ISIT (2015)
Yi Ouyang, Demosthenis Teneketzis
On the Optimality of Myopic Sensing in Multi-State Channels. IEEE Trans. Inf. Theory 60 (1) (2014)
Yi Ouyang, Demosthenis Teneketzis
Balancing through signaling in decentralized routing. CDC (2014)
Yi Ouyang, Demosthenis Teneketzis
Signaling for Decentralized Routing in a Queueing Network. CoRR (2014)
Yi Ouyang, Demosthenis Teneketzis
On The Optimality of Myopic Sensing in Multi-State Channels CoRR (2013)
Yi Ouyang, Demosthenis Teneketzis
A routing problem in a simple queueing system with non-classical information structure. Allerton (2013)
Yi Ouyang, Demosthenis Teneketzis
On the optimality of a myopic policy in multi-state channel probing. Allerton Conference (2012)