DISCO: Double Likelihood-free Inference Stochastic Control
This work addresses the challenge of efficient and robust control for robotics and physical systems with intractable simulation models, though it is incremental as it builds on existing likelihood-free inference and control techniques.
The authors tackled the problem of controlling complex systems with uncertain simulation parameters by proposing a likelihood-free inference control framework, which achieved superior performance and robustness on classical control and robotics tasks compared to models ignoring parameter uncertainty.
Accurate simulation of complex physical systems enables the development, testing, and certification of control strategies before they are deployed into the real systems. As simulators become more advanced, the analytical tractability of the differential equations and associated numerical solvers incorporated in the simulations diminishes, making them difficult to analyse. A potential solution is the use of probabilistic inference to assess the uncertainty of the simulation parameters given real observations of the system. Unfortunately the likelihood function required for inference is generally expensive to compute or totally intractable. In this paper we propose to leverage the power of modern simulators and recent techniques in Bayesian statistics for likelihood-free inference to design a control framework that is efficient and robust with respect to the uncertainty over simulation parameters. The posterior distribution over simulation parameters is propagated through a potentially non-analytical model of the system with the unscented transform, and a variant of the information theoretical model predictive control. This approach provides a more efficient way to evaluate trajectory roll outs than Monte Carlo sampling, reducing the online computation burden. Experiments show that the controller proposed attained superior performance and robustness on classical control and robotics tasks when compared to models not accounting for the uncertainty over model parameters.