MODELING TASK UNCERTAINTY FOR SAFE META-IMITATION LEARNING

Modeling Task Uncertainty for Safe Meta-Imitation Learning

To endow robots with the flexibility to perform a wide range of tasks in diverse and complex environments, learning their controller from experience data is a promising approach.In particular, some recent meta-learning methods are shown to solve novel tasks by leveraging their experience of performing other tasks during training.Although studies ar

read more

Atomistic Study of Mechanical Behaviors of Carbon Honeycombs

With an ultralarge surface-to-volume ratio, a recently synthesized three-dimensional graphene structure, namely, carbon honeycomb, promises important engineering applications.Herein, we have investigated, via molecular dynamics simulations, its mechanical properties, which are inevitable for its Carriers integrity and desirable for any feasible imp

read more

Plant communities and food webs

Recent theoretical work has provided major new insights into the ways that species interactions in food webs are organized in ways that permit the PCA coexistence of significant numbers of species.But, we seem to have forgotten about trees! Not the phylogenetic ones that are increasingly important for dissecting the evolutionary structure of food w

read more