On Convex Data-Driven Inverse Optimal Control for Nonlinear, Non-stationary and Stochastic Systems
This addresses the challenge of cost inference in complex control systems, which is incremental as it builds on existing inverse control methods by handling more general system dynamics.
The paper tackled the problem of reconstructing non-convex, non-stationary costs from agent observations in inverse optimal control for nonlinear, stochastic systems, achieving this by solving a convex optimization problem and validating effectiveness through in-silico and hardware experiments.
This paper is concerned with a finite-horizon inverse control problem, which has the goal of reconstructing, from observations, the possibly non-convex and non-stationary cost driving the actions of an agent. In this context, we present a result enabling cost reconstruction by solving an optimization problem that is convex even when the agent cost is not and when the underlying dynamics is nonlinear, non-stationary and stochastic. To obtain this result, we also study a finite-horizon forward control problem that has randomized policies as decision variables. We turn our findings into algorithmic procedures and show the effectiveness of our approach via in-silico and hardware validations. All experiments confirm the effectiveness of our approach.