• DOI:10.1007/978-3-030-01270-0_3
Corpus ID: 3993448

Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation

@article{Wang2018LookBY,
  title={Look Before You Leap: Bridging Model-Free and Model-Based Reinforcement Learning for Planned-Ahead Vision-and-Language Navigation},
  author={Xin Eric Wang and Wenhan Xiong and Hongmin Wang and William Yang Wang},
  journal={ArXiv},
  year={2018},
  volume={abs/1803.07729}
}

Xin Eric Wang, Wenhan Xiong, +1 author William Yang Wang

Published 2018

Computer Science

ArXiv

Existing research studies on vision and language grounding for robot navigation focus on improving model-free deep reinforcement learning (DRL) models in synthetic environments. However, model-free DRL models do not consider the dynamics in the real-world environments, and they often fail to generalize to new scenes. In this paper, we take a radical approach to bridge the gap between synthetic studies and real-world practices---We propose a novel, planned-ahead hybrid reinforcement learning… CONTINUE READING

View PDF on arXiv

Save to Library

Create Alert

Cite

Launch Research Feed