Vision-and-Language Navigation (VLN) is a natural language grounding task where an agent learns to follow language instructions and navigate to specified destinations in realworld environments. A key challenge is to recognize and stop at the correct location, especially for complicated outdoor environments. Existing methods treat the STOP action equally as other actions, which results in undesirable behaviors that the agent often fails to stop at the destination even though it might be on the right path. Therefore, we propose Learning to Stop (L2STOP), a simple yet effective policy module that differentiates STOP and other actions. Our approach achieves the new state of the art on a challenging urban VLN dataset TOUCHDOWN, outperforming the baseline by 6.89% (absolute improvement) on Success weighted by Edit Distance (SED).
Steady-state numerical simulations of the dipole¯ow test in layered aquifers demonstrate that the test produces a good estimate of the equivalent hydraulic conductivity anisotropy ratio for the part of the aquifer spanned by the well chambers. The eects of chamber size, dierent conductivity of layers and layer location on the estimated anisotropy ratios are presented. The steady-state dipole¯ow test, when performed at dierent levels in the well, can yield estimates of the down-hole anisotropy ratio distribution. Numerical simulations also illustrate that the skin eect can signi®cantly distort the anisotropy estimates produced by the dipole¯ow test.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.