Neural Modular Control for Embodied Question Answering

26 Oct 2018Abhishek Das • Georgia Gkioxari • Stefan Lee • Devi Parikh • Dhruv Batra

We present a modular approach for learning policies for navigation over long planning horizons from language input. Independent reinforcement learning at each level of hierarchy enables sub-policies to adapt to consequences of their actions and recover from errors. Subsequent joint hierarchical training enables the master policy to adapt to the sub-policies.

Full paper

Evaluation


No evaluation results yet. Help compare this paper to other papers by submitting the tasks and evaluation metrics from the paper.