[Google Scholar]
Time-variation in Online Nonconvex Optimization Enables Escaping from Spurious Local Minima Y. Ding, J. Lavaei, and M. Arcak IEEE Transactions on Automatic Control (long paper), 2021.
On the Absence of Spurious Local Trajectories in Time-varying Nonconvex Optimization S. Fattahi, C. Josz, Y. Ding, R. Mohammadi, J. Lavaei, and S. Sojoudi IEEE Transactions on Automatic Control (long paper), 2021.
Beyond Exact Gradients: Convergence of Stochastic Soft-Max Policy Gradient Methods with Entropy Regularization Y. Ding, J. Zhang, H. Lee, and J. Lavaei IEEE Transactions on Automatic Control (long paper), 2024 (to appear).
The Landscape of the Optimal Control Problem: One-shot Optimization Versus Dynamic Programming J. Kim, Y. Ding, Y. Bi, and J. Lavaei IEEE Transactions on Automatic Control (long paper), 2024.
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation S. Gu, L. Shi, Y. Ding, A. Knoll, C. Spanos, A. Wierman, M. Jin Conference on Neural Information Processing Systems (NeurIPS) 2024 (to appear).
Balance Reward and Safety Optimization for Safe Reinforcement Learning: A Perspective of Gradient Manipulation S. Gu, B, Sel, Y. Ding, L. Wang, Q. Lin, M. Jin, A. Knoll AAAI Conference on Artificial Intelligence (AAAI), 2024. (Oral)
Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities D. Ying, Y. Zhang, Y. Ding, A. Koppel, and J. Lavaei Conference on Neural Information Processing Systems (NeurIPS) 2023.
Tempo Adaption in Non-stationary Reinforcement Learning H. Lee, Y. Ding, J. Lee, M. Jin, J. Lavaei, and S. Sojoudi Conference on Neural Information Processing Systems (NeurIPS) 2023.
Learning-to-Learn to Guide Random Search: Derivative-Free Meta Blackbox Optimization on Manifold B. Sel, A. Tawaha, Y. Ding, R. Jia, B. Ji, J. Lavaei, and M. Jin Learning for Dynamics & Control Conference (L4DC) 2023. (Oral)
Local Analysis of Entropy-Regularized Stochastic Soft-Max Policy Gradient Methods Y. Ding, J. Zhang, and J. Lavaei European Control Conference(ECC) 2023.
A CMDP-within-online framework for Meta-Safe Reinforcement Learning V. Khattar, Y. Ding, B. Sel, J. Lavaei, and J. Ming International Conference on Learning Representations (ICLR) 2023. (Spotlight)
Scalable Multi-Agent Reinforcement Learning with General Utilities D. Ying, Y. Ding, A. Koppel, and J. Lavaei American Control Conference (ACC) 2023.
Non-stationary Risk-sensitive Reinforcement Learning: Near-optimal Dynamic Regret, Adaptive Detection, and Separation Design Y. Ding, J. Ming, and J. Lavaei AAAI Conference on Artificial Intelligence (AAAI), 2023. (Oral)
Provably Efficient Primal-Dual Reinforcement Learning for CMDPs with Non-stationary Objectives and Constraints Y. Ding and J. Lavaei AAAI Conference on Artificial Intelligence (AAAI), 2023.
Policy-based Primal-Dual Methods for Convex Constrained Markov Decision Processes D. Ying, M. Guo, Y. Ding, J. Lavaei, and Zuo-Jun (Max) Shen AAAI Conference on Artificial Intelligence (AAAI), 2023.
On the Global Optimum Convergence of Momentum-based Policy Gradient Y. Ding, J. Zhang, and J. Lavaei International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
A Dual Approach to Constrained Markov Decision Processes With Entropy Regularization. D. Ying, Y. Ding, and J. Lavaei International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
Structured Projection-free Online Convex Optimization with Multi-Point Bandit Feedback Y. Ding, and J. Lavaei IEEE conference on Decision and Control (CDC), 2021.
Analysis of Spurious Local Solutions of Optimal Control Problems: One-Shot Optimization Versus Dynamic Programming Y. Ding, Y. Bi, and J. Lavaei American Control Conference (ACC). IEEE, 2021.
Escaping spurious local minimum trajectories in online time-varying nonconvex optimization Y. Ding, J. Lavaei and M. Arcak American Control Conference (ACC). IEEE, 2021. (Finalist for Best Student Paper Award)
Input Design for Nonlinear Model Discrimination via Affine Abstraction K. Singh, Y. Ding, N. Ozay, S.Z. Yong. Proc. 6th IFAC Conference on Analysis and Design of Hybrid Systems (ADHS), Oxford, UK, July 2018.
Optimal Input Design for Affine Model Discrimination with Applications in Intention-Aware Vehicles Y. Ding, F. Harirchi, S.Z. Yong, E. Jacobsen, N. Ozay 9th ACM/IEEE International Conference on Cyber-Physical Systems (ICCPS), Porto, Portugal, April 2018.
Dynamic Ensembling for Probabilistic Time Series Forecasting via Deep Reinforcement Learning. Y. Ding, Y. Park, K. Gopalswamy, H. Hasson, Y. Wang, and L. Huan MILETS workshop at Knowledge Discovery and Data Mining Conference (KDD) 2023.
Policy-based Primal-Dual Methods for Concave CMDP with Variance Reduction D. Ying, M. Guo, H. Lee, Y. Ding, J. Lavaei, and Zuo-Jun (Max) Shen
Safe and Balanced: A Framework for Constrained Multi-Objective Reinforcement Learning S. Gu, B, Sel, Y. Ding, L. Wang, Q. Lin, A. Knoll, M. Jin
Aggressive Local Search for Constrained Optimal Control Problems with Many Local Minima Y. Ding, F. Han, and J. Lavaei