Publications
Preprints
Miguel Calvo-Fullana, Santiago Paternain, Luiz F.O. Chamon and Alejandro Ribeiro. “State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards”, arXiv Pre-print February 2021.
Clark Zhang, Santiago Paternain , and Alejandro Ribeiro. “Sufficiently Accurate Model Learning for Planning”, IEEE Robotic Letters. February 2021 (Under Review)
Harshat Kumar, Santiago Paternain and Alejandro Ribeiro. “Navigation of a Quadratic Potential with Ellipsoidal Obstacles”, Automatica. August 2020 (Accepted)
Bruno A. Angélico, Luiz F.O. Chamon, Santiago Paternain , Daniel Mox, Alejandro Ribeiro and George J. Pappas. “Gradient Free Source Seeking in Spherical Worlds with Convex Obstacles”, IEEE Transactions on Mechatronics. March 2020 (Under Review)
Santiago Paternain , Manfred Morari and Alejandro Ribeiro. “A Prediction-Correction Algorithm for Real-Time Model Predictive Control”, IEEE Transactions on Automatic Control. November
2019 (Under Review)
Journals
Santiago Paternain , Miguel Calvo-Fullana, Luiz F.O. Chamon and Alejandro Ribeiro. “Safe Policies for Reinforcement Learning Via Primal-Dual methods”, IEEE Transactions on Automatic Control. (To appear April 2023)
Santiago Paternain , Juan Andrés Bazerque and Alejandro Ribeiro. “Policy Gradient for Continuing Tasks in Discounted Markov Decision Processes”, IEEE Transactions on Automatic Control, vol:67, issue:9 September 2022, pp 4467–4482.
Luiz F.O. Chamon, Santiago Paternain, Miguel Calvo-Fullana and Alejandro Ribeiro. “Constrained Learning with Non-Convex Losses”, IEEE Transactions on Information Theory. July 2022 (Early Access).
Santiago Paternain , Juan Andrés Bazerque, Austin Small and Alejandro Ribeiro. “Stochastic
Policy Gradient Ascent in Reproducing Kernel Hilbert Spaces”,
IEEE Transactions on Automatic Control, vol:66, issue:8 August 2021, pp 3429–3444.
Andrea Simonetto, Emiliano Dall'Anese, Santiago Paternain , Geert Leus and Georgios B.
Giannakis. “Time-Varying Convex Optimization: Time-Structured Algorithms and Applications”,
IEEE Proceedings of the IEEE vol:108, issue:11, November 2020 pp. 2032–2048.
Santiago Paternain , Soomin Lee, Michael M. Zavlanos and Alejandro Ribeiro. “Distributed
Constrained Online Learning”, IEEE Transactions on Signal Processing vol:68, issue: 6, June 2020, pp. 3486 - 3499.
Maria Peifer, Luiz F.O. Chamon, Santiago Paternain and Alejandro Ribeiro. “Sparse Multi-
resolution representations with Adaptive Kernels”, IEEE Transactions on Signal Processing, vol:68, February 2020, pp.2031-2044.
Santiago Paternain and Alejandro Ribeiro. “Stochastic Artificial Potentials for Online Safe
Navigation”, IEEE Transactions on Automatic Control, vol: 65, issue: 5, May 2020,pp.1985–2000.
Santiago Paternain , Aryan Mokhtari and Alejandro Ribeiro. “A Newton-Based Method for
Nonconvex Optimization with Fast Evasion of Saddle Points”, SIAM, Journal on Optimization, vol:29,No.1 January 2019, pp.343-368.
Santiago Paternain, Daniel E. Koditschek and Alejandro Ribeiro. “Navigation Functions for
Convex Potentials in a Space with Convex Obstacles”, IEEE Transactions on Automatic Control,
vol:63, issue: 9 September 2018 p.2944-2959.
Mahyar Fazlyab, Santiago Paternain , Victor M. Preciado and Alejandro Ribeiro.“Prediction-
Correction Interior-Point Method for Time-Varying Convex Optimization”, IEEE Transactions on
Automatic Control, vol:63, issue: 7 July 2018 p.1973-1986.
Alec Koppel, Santiago Paternain , Cedric Richard and Alejandro Ribeiro. “Decentralized Online Learning with Kernels”, IEEE Transactions on Signal Processing, vol:66, issue: 12 June 2018 p.3240-3255.
Santiago Paternain and Alejandro Ribeiro. “Online Learning of Feasible Strategies in Unknown Environments”, IEEE Transactions on Automatic Control, vol:62, issue:6 June 2017 p.2807-
2822.
Conferences
Miguel Calvo-Fullana, Santiago Paternain, Luiz FO. Chamon and Alejandro Ribeiro. “State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards”. 33rd Conference on Neural Information Processing Systems, workshop on Safe and Robust Control of Uncertain Systems. Virtual conference, December 6–14,2021.
Miguel-Calvo-Fullana, Luiz F.O. Chamon and Santiago Paternain. “Towards Safe Continuing Task Reinforcement Learning” In Proc. 2021 American Control Conference, pp. 902-908. New Orleands, LA, May 26–28, 2021.
Bruno Angelico, Luiz F. O. Chamon, Santiago Paternain, Alejandro Ribeiro, George J. Pappas.“Source Seeking in Unknown Environments with Convex Obstacles”. In Proc. 2021 American Control Conference, pp. 5055-5061. New Orleands, LA, May 26–28, 2021.
Luiz F.O. Chamon,Santiago Paternain , Alexandre Amice and Alejandro Ribeiro. “Resilient Control: Compromising to Adapt”, In Proc. 58th Conference on Decision and Control, pp. 5703-5710. Jeju, Korea, December 8-11,2020.
Luiz F.O. Chamon, Santiago Paternain , Miguel Calvo-Fullana and Alejandro Ribeiro. “The Empirical Duality Gap of Constrained Statistical Learning”. In Proc. 45th International Conference on Acoustics, Speech, and Signal Processing, Barcelona, pp. 8474-8378. Spain, May 4-8 2020. (Best Student Paper Award) .
Harshat Kumar, Santiago Paternain and Alejandro Ribeiro. “Navigation of a QuadraticPotential with Star Obstacles”. In Proc. 2020 American Control Conference pp. 2043-2048. Denver, Colorado, July 1-3 2020.
Clark Zhang, Arbaaz Khan, Santiago Paternain and Alejandro Ribeiro. “Sufficiently Accurate
Model Learning”. In Proc. 2020 International Conference on Robotics and Automation, 10991-10997. Paris, France, May 31-June 4,2020.
Luiz F.O. Chamon, Santiago Paternain and Alejandro Ribeiro. “Counterfactual Programming for Optimal Control”. In Proc. Learning for Dynamics and Control, vol. 120, pp. 235-244, Berkley, CA, June 10-11 2020.
Santiago Paternain , Miguel Calvo-Fullana, Luiz F.O. Chamon and Alejandro Ribeiro. “Constrained Reinforcement Learning Has Zero Duality Gap.” In Proc. 33rd Conference on Neural Information Processing Systems, vol. 7553-7563. Vancouver, Canada, December 8-14,2019.
Santiago Paternain , Miguel Calvo-Fullana, Luiz F.O. Chamon and Alejandro Ribeiro. “Learning Safe Policies Via Primal-Dual methods.” In Proc. 58th Conference on Decision and Control,
6491-6497. Nice, France, December 11-13,2019.
Santiago Paternain, Manfred Morari and Alejandro Ribeiro. “Real-Time Model Predictive Control Based on Prediction-Correction Algorithms”, In Proc. 58th Conference on Decision and
Control, vol. 5285-5291. Nice, France, December 11-13,2019. (Invited Session)
Santiago Paternain , Juan Andrés Bazerque, Austin Small and Alejandro Ribeiro. “Policy
Improvement Directions for Reinforcement Learning in Reproducing Kernel Hilbert Spaces.”
In Proc. 58th Conference on Decision and Control, 7454-7461. Nice France, December 11-13,2019.
Santiago Paternain , Soomin Lee, Michael M. Zavlanos and Alejandro Ribeiro. “Constrained Online Learning in Networks with Sublinear Regret and Fit”, In Proc. 58th Conference on Decision and Control, vol. 5486-5493. Nice, France, December 11-13,2019.
Harshat Kumar,Santiago Paternain and Alejandro Ribeiro. “Navigation of Quadratic Potentials with Ellipsoidal Obstacles”, In Proc. 58th Conference on Decision and Control, vol. 4777-4784. Nice, France, December 11-13,2019.
Luiz F.O. Chamon, Santiago Paternain and Alejandro Ribeiro. “Bayesian Model Learning for Gaussian Processes: Optimizing your way to a posterior”. In Proc. IEEE Asilomar Conference
on Signals, Systems and Computers, vol. 482-486, Paciffic Grove, CA, November 3-6 2019.
Santiago Paternain , Mahyar Fazlyab, Victor M. Preciado and Alejandro Ribeiro. “A Prediction-Correction Primal-Dual Algorithm for Distributed Optimization”. In Proc. American Control Conference, vol. 835-841. Philadelphia, PA, July 10-12 2019.
Maria Peifer, Luiz F.O. Chamon, Santiago Paternain and Alejandro Ribeiro. “Sparse Learning of Parsimonious Reproducing Kernel Hilbert Space Models”. In Proc. IEEE International Conference on Acoustics, Speech and Signal Processing, p.3292-3296. Brighton, UK, May 12-17 2019.
Santiago Paternain , Juan Andrés Bazerque, Austin Small and Alejandro Ribeiro. “Learning Policies for Markov Decision Processes in Continuous Spaces”. In Proc. IEEE 57th Annual Conference on Decision and Control (CDC), vol. 4751-4758. Miami, FL, December 17-19 2018.
Santiago Paternain , Aryan Mokthari and Alejandro Ribeiro. “A Newton Method for Faster Navigation in Cluttered Environments”. In Proc. IEEE 57th Annual Conference on Decision and
Control (CDC), vol. 4084-4090. Miami, FL, December 17-19 2018.
Alec Koppel, Santiago Paternain, Cedric Richard and Alejandro Ribeiro. “Decentralized Online Nonparametric Learning”, In Proc. IEEE Asilomar Conference on Signals, Systems and
Computers, vol. 2139-2143. Paciffic Grove, CA, October 28-31 2018. (Invited Session)
Maria Peifer, Luiz F.O. Chamon, Santiago Paternain and Alejandro Ribeiro. “Locally Adaptive Kernel Estimation Using Sparse Functional Programming”, In Proc. IEEE Asilomar Conference
on Signals, Systems and Computers, vol. 2022-2026. Paciffic Grove, CA, October 28-31 2018.
Santiago Paternain , Manfred Morari and Alejandro Ribeiro. “A Prediction-Correction Method for Model Predictive Control”, In Proc. American Control Conference, vol. 4189-4194. Milwaukee, WI, June 27-29 2018.
Mahyar Fazlyab, Santiago Paternain, Alejandro Ribeiro and Victor M. Preciado. “Distributed
Smooth and Strongly Convex Optimization with Inexact Dual Methods”, In Proc. American Control Conference, vol. 3768-3773 Milwaukee, WI, June 27-29 2018.
Santiago Paternain and Alejandro Ribeiro “Safe Online Navigation of Convex Potentials in
Spaces with Convex Obstacles”, In proc. 56th Annual Conference on Decision and Control, vol.2473- 2478. Melbourne, Australia. December 12-16 2017. (Best Student Paper Award).
Alec Koppel, Santiago Paternain, Cedric Richard and Alejandro Ribeiro. “Decentralized Efficient Nonparametric Stochastic Optimization”. In Proc. 5th IEEE Global Conference on Signal and Information Processing , vol: 533-537. Montreal, Canada, November 14-16 2017.
Santiago Paternain, Matías Tailanián, Rodrigo Rosa and Rafael Canetti. “Design and Implementation of Flight Control for an Autonomous Quadrotor”, In Proc. 2017 IEEE URUCON , vol.1-4. Montevideo, Uruguay, 23-25 October 2017.
Mahyar Fazlyab, Santiago Paternain, Victor M. Preciado and Alejandro Ribeiro. “Interior
Point Method for Dynamic Constrained Optimization in Continuous Time”, In Proc. American Control Conference, vol. 5612-5618. Boston, July 6-8 2015.
Santiago Paternain and Alejandro Ribeiro. “Online Learning of Optimal Strategies in Unknown Environments”, In Proc. 54th Annual Conference on Decision and Control , vol. 3951-3958.
Osaka, Japan. December 15-18 2015.
Santiago Paternain and Alejandro Ribeiro. “Online Learning of Feasible Strategies in Unknown Environments”. In Proc. American Control Conference , vol. 4231-4238, Chicago, United States. July 1-3 2015.
Matías Tailanián, Santiago Paternain, Rodrigo Rosa and Rafael Canetti. “Design and Implementation of Sensor Data Fusion for an Autonomous Quadrotor”, In Proc Instrumentation and
Measurement Technology Conference (I2MTC) , vol. 1431-1436. Montevideo, Uruguay May 12-15 2014
(Best Student Paper Award).
Santiago Paternain , Matías Tailanián and Rafael Canetti. “Calibration of an Inertial Measurement Unit”, In Proc International Conference on Advanced Robotics (ICAR) , vol. 1-6. Montevideo, Uruguay November 25-29 2013.
|