← Back to Benchmarks
simmediumaerialmetric · varies

DoShiCo Challenge: Domain Shift in Control Prediction

Description

Training deep neural network policies end-to-end for real-world applications so far requires big demonstration datasets in the real world or big sets consisting of a large variety of realistic and closely related 3D CAD models. These real or virtual data should, moreover, have very similar characteristics to the conditions expected at test time. These stringent requirements and the time consuming data collection processes that they entail, are currently the most important impediment that keeps d

Source

http://arxiv.org/abs/1710.09860v2