Some questions about the input observation
wxz1996 opened this issue · 1 comments
wxz1996 commented
Hi, I have a question, why do VIMA need both frontal and top-down views for the observation space,Can't just only give the top?
yunfanjiang commented
Hi there. For certain tasks only supplying top-down view might be suboptimal, such as Follow Order
where one object is stacked on another. Additionally, due to legacy reason, we used to have tasks where frontal view is necessary to provide enough information for reasoning.