Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs
This work addresses a limitation in modeling sequential decision-making for non-linear partially observable systems, with applications in imitation learning and sensorimotor neuroscience, though it appears incremental as it builds on existing maximum causal entropy formulations.
The authors tackled the problem of inverse optimal control for partially observable, stochastic non-linear systems with unobserved actions by introducing a probabilistic approach that unifies previous methods and uses local linearization to compute an approximate likelihood efficiently. They demonstrated the method on classic control and human behavioral tasks, showing it can disentangle perceptual uncertainty from behavioral costs, with quantitative evaluations provided.
Inverse optimal control can be used to characterize behavior in sequential decision-making tasks. Most existing work, however, is limited to fully observable or linear systems, or requires the action signals to be known. Here, we introduce a probabilistic approach to inverse optimal control for partially observable stochastic non-linear systems with unobserved action signals, which unifies previous approaches to inverse optimal control with maximum causal entropy formulations. Using an explicit model of the noise characteristics of the sensory and motor systems of the agent in conjunction with local linearization techniques, we derive an approximate likelihood function for the model parameters, which can be computed within a single forward pass. We present quantitative evaluations on stochastic and partially observable versions of two classic control tasks and two human behavioral tasks. Importantly, we show that our method can disentangle perceptual factors and behavioral costs despite the fact that epistemic and pragmatic actions are intertwined in sequential decision-making under uncertainty, such as in active sensing and active learning. The proposed method has broad applicability, ranging from imitation learning to sensorimotor neuroscience.