2026
Learning in Zero-Sum Markov Games: Relaxing Strong Reachability and Mixing Time Assumptions
Proceedings of the AAAI Conference on Artificial Intelligence. 2026. Vol. 40, num. 20, p. 17170 – 17178. DOI : 10.1609/aaai.v40i20.38767.Finite-time convergence to an ϵ-efficient Nash equilibrium in potential games
IEEE Transactions on Control of Network Systems. 2026. p. 1 – 12. DOI : 10.1109/TCNS.2026.3673502.Finite-time convergence to an $\epsilon$-efficient Nash equilibrium in potential games
IEEE Transactions on Control of Network Systems. 2026. p. 1 – 12. DOI : 10.1109/tcns.2026.3673502.Game-Theoretic Decision Making in Multi-Agent Systems under Constraints and Welfare Objectives
Lausanne, EPFL, 2026.2025
No-Regret Learning in Stackelberg Games with an Application to Electric Ride-Hailing
2025. 2025 IEEE 64th Conference on Decision and Control (CDC), Rio de Janeiro, Brazil, 2025-12-09 – 2025-12-12. p. 4009 – 4014. DOI : 10.1109/cdc57313.2025.11312071.Rollout, Policy Iteration, and Distributed Reinforcement Learning [Book Review]
IEEE Control Systems. 2025. Vol. 45, num. 6, p. 134 – 136. DOI : 10.1109/mcs.2025.3615016.Deep learning-driven MRI for accurate brain volumetry in murine models of neurodegenerative diseases
Frontiers in Neuroscience. 2025. Vol. 19. DOI : 10.3389/fnins.2025.1632169.On Linear Quadratic Potential Games☆
AUTOMATICA. 2025. Vol. 183. DOI : 10.1016/j.automatica.2025.112643.Publisher’s Note
European Journal of Control. 2025. Vol. 85. DOI : 10.1016/j.ejcon.2025.101320.Learning to Assemble with Alternative Plans
ACM Transactions on Graphics. 2025. Vol. 44, num. 4, p. 1 – 16. DOI : 10.1145/3730824.Nash equilibria in scalar discrete-time linear quadratic games
2025. 2025 European Control Conference (ECC), Thessaloniki, Greece, 2025-06-24 – 2025-06-27. p. 2416 – 2421. DOI : 10.23919/ecc65951.2025.11187226.Efficient Preference-Based Reinforcement Learning: Randomized Exploration Meets Experimental Design
2025
A learning-based approach to stochastic optimal control under reach-avoid constraint
2025. 28th ACM International Conference on Hybrid Systems: Computation and Control (HSCC 2025)., Irvine CA USA, 2025-05-06 – 2025-05-09. p. 1 – 8. DOI : 10.1145/3716863.3718055.Safe optimization with grey-box information: Application to composites autoclave processing improvement on the fly
Composites Part C: Open Access. 2025. Vol. 16, p. 100560. DOI : 10.1016/j.jcomc.2025.100560.On the approximation of vector-valued functions by volume sampling
Journal of Complexity. 2025. Vol. 86, p. 101887. DOI : 10.1016/j.jco.2024.101887.Safe Zeroth-order Optimization Using Quadratic Local Approximations
AUTOMATICA. 2025. Vol. 174. DOI : 10.1016/j.automatica.2025.112141.Chance-Constrained Linear Quadratic Gaussian Games for Multi-Robot Interaction Under Uncertainty
IEEE Control Systems Letters. 2025. p. 1 – 1. DOI : 10.1109/lcsys.2025.3588090.On the Convergence of Gradient Descent in Scalar Two-Agent Infinite-Horizon LQ Games
IEEE Control Systems Letters. 2025. p. 1 – 1. DOI : 10.1109/lcsys.2025.3574107.2024
Convergence of a model-free entropy-regularized inverse reinforcement learning algorithm
2024. 63rd IEEE Conference on Decision and Control, Milan, Italy, 2024-12-16 – 2024-12-19. p. 8258 – 8263. DOI : 10.1109/CDC56724.2024.10886001.Aircraft Trajectory Planning for Climate Hotspot Avoidance Considering Air Traffic Complexity: A Constrained Multi-Agent Reinforcement Learning Approach
2024. SESAR Innovation Days 2024, Rome, 2024-11-12 – 2024-11-15.Recursively Feasible Chance-Constrained Model Predictive Control Under Gaussian Mixture Model Uncertainty
IEEE Transactions on Control Systems Technology. 2024. p. 1 – 14. DOI : 10.1109/TCST.2024.3477089.Learning to bid in forward electricity markets using a no-regret algorithm
Electric Power Systems Research. 2024. Vol. 234, p. 110693. DOI : 10.1016/j.epsr.2024.110693.A Distributed Augmenting Path Approach for the Bottleneck Assignment Problem
Ieee Transactions On Automatic Control. 2024. Vol. 69, num. 2, p. 1210 – 1217. DOI : 10.1109/TAC.2023.3279336.Payoff-Based Learning of Nash Equilibria in Merely Monotone Games
IEEE Transactions on Control of Network Systems. 2024. p. 1 – 12. DOI : 10.1109/TCNS.2024.3355035.Multi-Agent Learning in Contextual Games under Unknown Constraints
2024. 27th International Conference on Artificial Intelligence and Statistics, Palau de Congressos, Valencia, Spain, 2024-05-02 – 2024-05-04.Towards the Transferability of Rewards Recovered Via Regularized Inverse Reinforcement Learning
2024. 38th Annual Conference on Neural Information Processing Systems, Vancouver Convention Center, 2024-12-10 – 2024-12-15.2023
Reinforcement learning for scaffold-free construction of spanning-structures
2023. 8th ACM Symposium on Computational Fabrication (SCF), New York, NY, OCT 08-10, 2023. DOI : 10.1145/3623263.3623359.Certification of Bottleneck Task Assignment With Shortest Path Criteria
IEEE Robotics and Automation. 2023. Vol. 8, p. 4545 – 4552. DOI : 10.1109/LRA.2023.3286815.Provable Convergence Guarantees for Constrained Inverse Reinforcement Learning
2023.Constrained Inverse Reinforcement Learning: Challenges and Solutions for Real World Implementation
2023.Learning to make mixed-integer robot motion planning easy
2023.Multi-agent Reinforcement Learning for Assembly of a Spanning Structure
2023.Identifiability and Generalizability in Constrained Inverse Reinforcement Learning
2023. International Conference on Machine Learning, Honolulu, Hawaï, July 23-29, 2023.Data-Driven Behaviour Estimation in Parametric Games
2023. 22nd World Congress of the International Federation of Automatic Control (IFAC), Yokohama, JAPAN, JUL 09-14, 2023. p. 9330 – 9335. DOI : 10.1016/j.ifacol.2023.10.220.Multi-robot task allocation for safe planning against stochastic hazard dynamics
2023. European Control Conference (ECC), Bucharest, Romania, June 13-16, 2023. DOI : 10.23919/ECC57647.2023.10178126.Safe Zeroth-Order Convex Optimization Using Quadratic Local Approximations
2023. 21st European Control Conference – ECC2023, Bucharest, Romania, June 13-16, 2023. DOI : 10.23919/ECC57647.2023.10178374.2022
Enabling inter-area reserve exchange through stable benefit allocation mechanisms *
Omega-International Journal Of Management Science. 2022. Vol. 113, p. 102711. DOI : 10.1016/j.omega.2022.102711.Iterative Graph Deformation for Aircraft Trajectory Planning Considering Ensemble Forecasting of Thunderstorms
SSRN Electronic Journal. 2022. DOI : 10.2139/ssrn.4215235.Optimal Task Assignment and Collision Avoidance for Mobile Robots
2022.Coordination and control of a group of ground robots
2022.Chance-Constrained Trajectory Planning With Multimodal Environmental Uncertainty
Ieee Control Systems Letters. 2022. Vol. 7, p. 13 – 18. DOI : 10.1109/LCSYS.2022.3186269.A greedy and distributable approach to the Lexicographic Bottleneck Assignment Problem with conditions on exactness
Automatica. 2022. Vol. 140, p. 110240. DOI : 10.1016/j.automatica.2022.110240.Efficient Model-based Multi-agent Reinforcement Learning via Optimistic Equilibrium Computation
2022. 38th International Conference on Machine Learning (ICML), Baltimore, MD, Jul 17-23, 2022. p. 19580 – 19597.Safe Motion Planning against Multimodal Distributions Based on a Scenario Approach
IEEE Control Systems Letters. 2022. Vol. 6, p. 1142 – 1147. DOI : 10.1109/LCSYS.2021.3089641.2021
Online Submodular Resource Allocation with Applications to Rebalancing Shared Mobility Systems
2021. International Conference on Machine Learning, 2021-07-01. p. 9455 – 9464.Fast Projection Onto Convex Smooth Constraints
2021. International Conference on Machine Learning, 2021-07-01. p. 10476 – 10486.Sample Complexity of Linear Quadratic Gaussian (LQG) Control for Output Feedback Systems
2021. Learning for Dynamics and Control, 2021-05-29. p. 559 – 570.Multi-robot task allocation for safe planning against stochastic hazard dynamics
2021
Bandit Online Learning of Nash Equilibria in Monotone Games
2021
RRT*-Based Algorithm for Trajectory Planning Considering Probabilistic Weather Forecasts
Lecture Notes in Electrical Engineering. 2021. Vol. 731 LNEE, p. 245 – 258. DOI : 10.1007/978-981-33-4669-7_14.Performance guarantees of forward and reverse greedy algorithms for minimizing nonsupermodular nonsubmodular functions on a matroid
Operations Research Letters. 2021. Vol. 49, num. 6, p. 855 – 861. DOI : 10.1016/j.orl.2021.09.006.Trajectory planning under environmental uncertainty with finite-sample safety guarantees
Automatica. 2021. Vol. 131, p. 109754. DOI : 10.1016/j.automatica.2021.109754.A market-based approach for enabling inter-area reserve exchange
Operations Research Letters. 2021. Vol. 49, num. 4, p. 501 – 506. DOI : 10.1016/j.orl.2021.05.009.On the Equivalence of Youla, System-Level, and Input-Output Parameterizations
IEEE Transactions on Automatic Control. 2021. Vol. 66, num. 1, p. 413 – 420. DOI : 10.1109/TAC.2020.2979785.Informed scenario-based RRT∗ for aircraft trajectory planning under ensemble forecasting of thunderstorms
Transportation Research Part C: Emerging Technologies. 2021. Vol. 129, p. 103232. DOI : 10.1016/j.trc.2021.103232.2020
Safe non-smooth black-box optimization with application to policy search
2020. Learning for Dynamics and Control, 2020-07-31. p. 980 – 989.Learning the Globally Optimal Distributed LQ Regulator
2020. Learning for Dynamics and Control, 2020-07-31. p. 287 – 297.First Order Methods For Globally Optimal Distributed Controllers Beyond Quadratic Invariance
2020. 2020 American Control Conference (ACC), Denver, CO, USA, 2020-07. p. 4588 – 4593. DOI : 10.23919/ACC45564.2020.9147358.Mixed Strategies for Robust Optimization of Unknown Objectives
2020. International Conference on Artificial Intelligence and Statistics, 2020-06-03. p. 2970 – 2980.Distributed Design for Decentralized Control using Chordal Decomposition and ADMM
IEEE Transactions on Control of Network Systems. 2020. Vol. 7, num. 2, p. 614 – 626. DOI : 10.1109/TCNS.2019.2935618.System-level, Input-output and New Parameterizations of Stabilizing Controllers, and Their Numerical Computation
2020
Minimizing Regret of Bandit Online Optimization in Unconstrained Action Spaces
2020
Core-Selecting Mechanisms in Electricity Markets
IEEE Transactions on Smart Grid. 2020. Vol. 11, num. 3, p. 2604 – 2614. DOI : 10.1109/TSG.2019.2958710.Safe Mission Planning under Dynamical Uncertainties
2020. 2020 IEEE International Conference on Robotics and Automation (ICRA), Paris, France, 2020-05. p. 2209 – 2215. DOI : 10.1109/ICRA40945.2020.9196515.Contextual Games: Multi-Agent Learning with Side Information
2020. p. 21912 – 21922.Learning to Play Sequential Games versus Unknown Opponents
2020. p. 8971 – 8981.Sparsity Invariance for Convex Design of Distributed Controllers
IEEE Transactions on Control of Network Systems. 2020. Vol. 7, num. 4, p. 1836 – 1847. DOI : 10.1109/TCNS.2020.3002429.Actuator Placement under Structural Controllability using Forward and Reverse Greedy Algorithms
IEEE Transactions on Automatic Control. 2020. p. 1 – 1. DOI : 10.1109/TAC.2020.3044284.A Multiagent Model of Efficient and Sustainable Financial Markets
2020. Machine Learning for Economic Policy workshop, Vancouver, 2020.No-Regret Learning from Partially Observed Data in Repeated Auctions
IFAC-PapersOnLine. 2020. Vol. 53, num. 2, p. 14 – 19. DOI : 10.1016/j.ifacol.2020.12.029.2019
Enabling inter-area reserve exchange through stable benefit allocation mechanisms
2019
Privacy of Real-Time Pricing in Smart Grid
2019. 2019 IEEE 58th Conference on Decision and Control (CDC), Nice, France, 2019-12. p. 5162 – 5167. DOI : 10.1109/CDC40024.2019.9029924.Log Barriers for Safe Non-convex Black-box Optimization
2019
Actuator Placement for Optimizing Network Performance under Controllability Constraints
2019. 2019 IEEE 58th Conference on Decision and Control (CDC), Nice, France, 2019-12. p. 7140 – 7147. DOI : 10.1109/CDC40024.2019.9030204.Unified Approach to Convex Robust Distributed Control Given Arbitrary Information Structures
IEEE Transactions on Automatic Control. 2019. Vol. 64, num. 12, p. 5199 – 5206. DOI : 10.1109/TAC.2019.2911655.Learning Nash Equilibria in Monotone Games
2019. 2019 IEEE 58th Conference on Decision and Control (CDC), Nice, France, 2019-12. p. 3104 – 3109. DOI : 10.1109/CDC40024.2019.9029659.Designing Coalition-Proof Reverse Auctions Over Continuous Goods
IEEE Transactions on Automatic Control. 2019. Vol. 64, num. 11, p. 4803 – 4810. DOI : 10.1109/TAC.2019.2908717.An Input–Output Parametrization of Stabilizing Controllers: Amidst Youla and System Level Synthesis
IEEE Control Systems Letters. 2019. Vol. 3, num. 4, p. 1014 – 1019. DOI : 10.1109/LCSYS.2019.2920205.Exploiting structure of chance constrained programs via submodularity
Automatica. 2019. Vol. 105, p. 89 – 95. DOI : 10.1016/j.automatica.2019.03.027.Strengthening the Group: Aggregated Frequency Reserve Bidding With ADMM
IEEE Transactions on Smart Grid. 2019. Vol. 10, num. 4, p. 3860 – 3869. DOI : 10.1109/TSG.2018.2841508.Robust aircraft trajectory planning under uncertain convective environments with optimal control and rapidly developing thunderstorms
Aerospace Science and Technology. 2019. Vol. 89, p. 445 – 459. DOI : 10.1016/j.ast.2019.03.051.On Separable Quadratic Lyapunov Functions for Convex Design of Distributed Controllers
2019. 2019 18th European Control Conference (ECC), Naples, Italy, 2019-06. p. 42 – 49. DOI : 10.23919/ECC.2019.8796100.Performance guarantees for greedy maximization of non-submodular controllability metrics
2019. 2019 18th European Control Conference (ECC), Naples, Italy, 2019-06. p. 2796 – 2801. DOI : 10.23919/ECC.2019.8795800.Using Uncertainty Data in Chance-Constrained Trajectory Planning
2019. 2019 18th European Control Conference (ECC), Naples, Italy, 2019-06. p. 2264 – 2269. DOI : 10.23919/ECC.2019.8795823.Bounding Inefficiency of Equilibria in Continuous Actions Games using Submodularity and Curvature
2019. The 22nd International Conference on Artificial Intelligence and Statistics, 2019-04-11. p. 2017 – 2027.Safe Convex Learning under Uncertain Constraints
2019. The 22nd International Conference on Artificial Intelligence and Statistics, 2019-04-11. p. 2106 – 2114.Learning Generalized Nash Equilibria in a Class of Convex Games
IEEE Transactions on Automatic Control. 2019. Vol. 64, num. 4, p. 1426 – 1439. DOI : 10.1109/TAC.2018.2841319.Nash and Wardrop Equilibria in Aggregative Games With Coupling Constraints
IEEE Transactions on Automatic Control. 2019. Vol. 64, num. 4, p. 1373 – 1388. DOI : 10.1109/TAC.2018.2849946.No-Regret Learning in Unknown Games with Correlated Payoffs
2019. Advances in Neural Information Processing System, Vancouver, 2019.2018
Exploiting Weak Supermodularity for Coalition-Proof Mechanisms
2018. 2018 IEEE Conference on Decision and Control (CDC), Miami Beach, FL, 2018-12. p. 1118 – 1123. DOI : 10.1109/CDC.2018.8619337.Robust Distributed Control Beyond Quadratic Invariance
2018. 2018 IEEE Conference on Decision and Control (CDC), Miami Beach, FL, 2018-12. p. 3728 – 3733. DOI : 10.1109/CDC.2018.8619137.Reducing HVDC Network Oscillations Considering Wind Intermittency Through Optimized Grid Expansion Decision
2018. 2018 IEEE Energy Conversion Congress and Exposition (ECCE), Portland, OR, USA, 2018-09. p. 2683 – 2690. DOI : 10.1109/ECCE.2018.8557546.On maximizing safety in stochastic aircraft trajectory planning with uncertain thunderstorm development
Aerospace Science and Technology. 2018. Vol. 79, p. 543 – 553. DOI : 10.1016/j.ast.2018.06.006.Game-theoretic models in energy systems and control DTU Summer School 2018 Modern Optimization in Energy Systems
2018