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.

Collaborators.

• Benoît Bonnet-Weill, CNRS and Université Paris-Saclay.
• Luc Brogat-Motte, Postdoctoral Scholar at Inria Paris and Université Paris-Saclay.
• Alessandro Rudi, Inria Paris and Bocconi University.

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.