On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets. (arXiv:2205.09249v1 [cs.CL])

Natural language guided embodied task completion is a challenging problem
since it requires understanding natural language instructions, aligning them
with egocentric visual observations, and choosing appropriate actions to
execute in the environment to produce desired changes. We experiment with
augmenting a transformer model for this task with modules that effectively
utilize a wider field of view and learn to choose whether the next step
requires a navigation or manipulation action. We observed that the proposed
modules resulted in improved, and …

arxiv model generalization validation