Generative Language-Grounded Policy in Vision-and-Language Navigation with Bayes' Rule
arXiv:2009.07783
Abstract
Vision-and-language navigation (VLN) is a task in which an agent is embodied in a realistic 3D environment and follows an instruction to reach the goal node. While most of the previous studies have built and investigated a discriminative approach, we notice that there are in fact two possible approaches to building such a VLN agent: discriminative \textit{and} generative. In this paper, we design and investigate a generative language-grounded policy which uses a language model to compute the distribution over all possible instructions i.e. all possible sequences of vocabulary tokens given action and the transition history. In experiments, we show that the proposed generative approach outperforms the discriminative approach in the Room-2-Room (R2R) and Room-4-Room (R4R) datasets, especially in the unseen environments. We further show that the combination of the generative and discriminative policies achieves close to the state-of-the art results in the R2R dataset, demonstrating that the generative and discriminative policies capture the different aspects of VLN.
arXiv comment13 pages, 8 figures
References in corpus (6)
- Language Models are Few-Shot Learners
- On Evaluation of Embodied Navigation Agents
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- Building Generalizable Agents with a Realistic and Rich 3D Environment
- Grounded Language Learning in a Simulated 3D World
- Self-Monitoring Navigation Agent via Auxiliary Progress Estimation