"Sim2Real DLO whipping rollouts of policies trained with and without a heuristically adapted domain support"

"Likelihood-free inference (LFI) enables system identification in complex tasks via black-box modelling, abstracting nonlinearity and stochasticity, and infers a domain distribution for adapting agents to parametric deployment conditions. LFI assumes an arbitrary support for sampling, which remains fixed as the initial generic prior is refined to increasingly descriptive posteriors. Misspecified support can therefore yield suboptimal yet overconfident posteriors. We address this issue by using the posterior of an inference step to heuristically guide the adaptation of the support in an approach which interprets the updated belief and enables support adaptation alongside posterior inference. This dataset features the evaluation of the posterior-driven heuristic support adaptation for parameter inference and policy learning in a dynamic deformable linear object manipulation task, which requires whipping the top of a stack of differently coloured cubes. We see that when the posteriors inferred over a heuristically adapted support are used as domain distributions for sim-based policy learning, they lead to more robust object-centric agent performance."