AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

Yangru Huang, Peixi Peng, Yifan Zhao, Haoran Xu, Mengyue Geng, Yonghong Tian

NeurIPS 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multi-modality image fusion · 3 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
replace GVE (global critic on concatenated features) with LVE (per-modality critics with learned contribution weights) (ablation)HAVE on RGB+event · CARLA ClearNightepisode return: 225 -> 274Improved
replace GVE with LVE (ablation)HAVE on RGB+event · CARLA WetNoonepisode return: 226 -> 296Improved
replace GVE with LVE (ablation)HAVE on RGB+event · CARLA CloudyNoonepisode return: 226 -> 293Improved
add task-contextual re-fusion of GVE and LVE on top of LVE alone (ablation)HAVE on RGB+event · CARLA ClearNightepisode return: 274 -> 319Improved
add task-contextual re-fusion on top of LVE (ablation)HAVE on RGB+event · CARLA WetNoonepisode return: 296 -> 341Improved
add task-contextual re-fusion on top of LVE (ablation)HAVE on RGB+event · CARLA WetNightdriving distance (m): 196 -> 222Improved
fuse RGB and event modalities with GVE instead of RGB alone (ablation)SAC encoder · CARLA ClearNightepisode return: 75 -> 225Improved
fuse RGB and event modalities with GVE instead of events alone (ablation)SAC encoder · CARLA ClearNightepisode return: 158 -> 225Improved
fuse RGB and event modalities with GVE instead of events alone (ablation)SAC encoder · CARLA WetNightepisode return: 175 -> 241No clear effect
use RGB frames only under adverse weather (ablation)SAC encoder · CARLA ClearNightepisode return: 75Hurt
HAVE vs best baseline (TransFuser) with learned fusion modulesHAVE · CARLA ClearNightepisode return: 260 -> 319Improved
HAVE vs best baseline (EFNet)HAVE · CARLA CloudyNightepisode return: 289 -> 322Improved

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