ROCH-Risk-averse Optimal Control via Homotopy

Consortium. Riccardo Bonalli (Project Investigator), CNRS and Université Paris-Saclay; Brandon Amos; Alessio Iovine, CNRS and Université Paris-Saclay; Marco Pavone, Stanford University.

Goal. This ANR JCJC project aims at developing both original reinforcement learning techniques to design reliable control models and novel stochastic optimal control tools to tackle non-convex risk-averse stochastic optimal control problems. The ultimate objective is to leverage and combine such new methods to devise a reliable and scalable algorithm called ROCH, for efficient and safe-against-uncertainty deployment of autonomous systems.

New open position! Call for one postoctoral position in stochastic analysis and statistical estimation
Topic. The goal is to devise novel techniques to perform non-parametric estimation for SDEs with irregular coefficients driven by Levy-type noises, thus possibly with jumps. When considering particularly regular coefficients and Brownian noise, RKHS-based estimators have been recently combined with the Fokker-Planck formalism to achieve non-asymptotic rates of convergence, e.g., [J6,J9]. The postdoc will investigate how to leverage the benefits of this approach, with the objective of deriving novel non-asymptotic rates of convergence in case of irregular, e.g., Cα, coefficients and ideally general Levy-type noises.
About the position. The position is for 18 months, with a gross monthly salary range of €2,500-€3,300. Starting date at the earliest convenience of the successful candidate, as of the 1st of January 2025. The postdoc will join L2S laboratory at Université Paris-Saclay and will be co-advised by Riccardo Bonalli (L2S, Université Paris-Saclay) and Alexandre Richard (MICS, Université Paris-Saclay).
How to apply. Applications should include a CV, a list of publications, a research statement and 2 letters of recommendation, to be sent to Riccardo Bonalli (riccardo.bonalli@centralesupelec.fr) and Alexandre Richard (alexandre.richard@centralesupelec.fr).

Collaborators.

Publications.

  1. L. Brogat-Motte, R. Bonalli, and A. Rudi, Learning Controlled Stochastic Differential Equations. Submitted.
  2. A. C. Morelli, C. Giordano, R. Bonalli, and F. Topputo, Characterization of Singular Arcs in Spacecraft Trajectory Optimization. Submitted.
  3. G. Velho, J. Auriol, and R. Bonalli, A Gradient Descent-Ascent Method for Continuous-Time Risk-Averse Optimal Control. Submitted.
  4. R. Bonalli and A. Rudi, Non-Parametric Learning of Stochastic Differential Equations with Fast Rates of Convergence. Submitted.
  5. T. Lew, R. Bonalli, and M. Pavone, Sample Average Approximation for Stochastic Programming with Equality Constraints. SIAM Journal on Optimization (2024), 4.
  6. C. Leparoux, R. Bonalli, B. Hérissé, and F. Jean, Statistical Linearization for Robust Motion Planning. Systems & Control Letters, 189 (2024), 105825.
  7. T. Lew, R. Bonalli, and M. Pavone, Risk-Averse Trajectory Optimization via Sample Average Approximation. IEEE Robotics and Automation Letters, 9 (2023), pp. 1500-1507.
  8. R. Bonalli, C. Leparoux, B. Hérissé, and F. Jean, On the Accessibility and Controllability of Statistical Linearization for Stochastic Control: Algebraic Rank Conditions and their Genericity. Mathematical Control and Related Fields, 14 (2024), pp. 648-670.
  9. R. Bonalli and B. Bonnet, First-Order Pontryagin Maximum Principle for Risk-Averse Stochastic Optimal Control Problems. SIAM Journal on Control and Optimization, 61 (2023), pp. 1881-1909.
  10. G. Velho, R. Bonalli, J. Auriol, and I. Boussaada, Mean-Covariance Steering of a Linear Stochastic System with Input Delay and Additive Noise. Proc. IEEE European Control Conference, 2024, Stockholm.