English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Inverse optimal control can be used to characterize behavior in sequentialdecision-making tasks. Most existing work, however, is limited to fullyobservable or linear systems, or requires the action signals to be known. Here,we introduce a probabilistic approach to inverse optimal control for partiallyobservable stochastic non-linear systems with unobserved action signals, whichunifies previous approaches to inverse optimal control with maximum causalentropy formulations. Using an explicit model of the noise characteristics ofthe sensory and motor systems of the agent in conjunction with locallinearization techniques, we derive an approximate likelihood function for themodel parameters, which can be computed within a single forward pass. Wepresent quantitative evaluations on stochastic and partially observableversions of two classic control tasks and two human behavioral tasks.Importantly, we show that our method can disentangle perceptual factors andbehavioral costs despite the fact that epistemic and pragmatic actions areintertwined in sequential decision-making under uncertainty, such as in activesensing and active learning. The proposed method has broad applicability,ranging from imitation learning to sensorimotor neuroscience.

Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs