AI Paper Atlas

Research map / Vision-language and multimodal / Robot action and navigation

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

Xin Wang, Wenhan Xiong, Hongmin Wang, William Yang Wang

ECCV 2018 · Vision-language and multimodal › Robot action and navigation · approach: Vision-language-action foundation models · 197 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add look-ahead module on top of model-free RLModel-free RL · R2R Val Unseensuccess rate (%): 21.5 -> 24.6Improved
add look-ahead module on top of model-free RLModel-free RL · R2R Val Seensuccess rate (%): 41.9 -> 42.9Improved
add look-ahead module on top of model-free RLModel-free RL · R2R Test (unseen)success rate (%): 23.1 -> 25.3Improved
add look-ahead module on top of model-free RLModel-free RL · R2R Val Unseennavigation error (m): 7.88 -> 7.65Improved
switch cross-entropy training to model-free RLXE · R2R Val Unseensuccess rate (%): 21.3 -> 21.5No clear effect
switch cross-entropy training to model-free RLXE · R2R Val Seensuccess rate (%): 40.2 -> 41.9Improved
use per-step discounted reward instead of global distance reward (ablation)Model-free RL · R2R Val Seensuccess rate (%): 35.5 -> 40.5Improved
use per-step discounted reward instead of binary success reward (ablation)Model-free RL · R2R Val Seensuccess rate (%): 37.8 -> 40.5Improved
add success reward to discounted reward (ablation)Model-free RL · R2R Val Seensuccess rate (%): 40.5 -> 41.9Improved
add success reward to discounted reward (ablation)Model-free RL · R2R Val Unseensuccess rate (%): 20.4 -> 21.5Improved
add success reward to discounted reward (ablation)Model-free RL · R2R Val Unseennavigation error (m): 7.74 -> 7.88Hurt
use per-step discounted reward instead of global distance reward (ablation)Model-free RL · R2R Val Unseensuccess rate (%): 19.0 -> 20.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy