AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Modeling 3D Shapes by Reinforcement Learning

Cheng Lin, Tingxiang Fan, Wenping Wang, Matthias Nießner

ECCV 2020 · Reinforcement learning › Visual and representation RL · approach: Scalable RL systems and environments · 36 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 imitation learning with virtual expert to RL-only training (ablation)Prim-Agent · ShapeNet Airplaneaverage accumulated reward: 0.377 -> 0.764Improved
add imitation learning with virtual expert to RL-only training (ablation)Mesh-Agent · ShapeNet Airplaneaverage accumulated reward: -0.013 -> 0.134Improved
add RL phase to interactive imitation learning (ablation)Mesh-Agent · ShapeNet Guitaraverage accumulated reward: 0.089 -> 0.204Improved
use interactive guidance instead of fixed demonstrations (ablation)Mesh-Agent · ShapeNet Airplaneaverage accumulated reward: 0.019 -> 0.134Improved
use interactive guidance instead of fixed demonstrations (ablation)Prim-Agent · ShapeNet Guitaraverage accumulated reward: 0.723 -> 0.987Improved
add double replay buffers to DAgger (ablation)Prim-Agent · ShapeNet Airplaneaverage accumulated reward: 0.574 -> 0.725Improved
add RL on top of DAgger with double replay buffers (ablation)Prim-Agent · ShapeNet Airplaneaverage accumulated reward: 0.725 -> 0.764Improved
full training strategy vs DAgger with double replay buffers (ablation)Mesh-Agent · ShapeNet GuitarIoU: 0.381 -> 0.512Improved
full training strategy vs DAgger with double replay buffers (ablation)Prim-Agent · ShapeNet AirplaneIoU: 0.131 -> 0.179Improved
use RGB image reference instead of depth mapPrim-Agent · ShapeNet Airplaneaverage accumulated reward: 0.764 -> 0.721No clear effect
use RGB image reference instead of depth mapMesh-Agent · ShapeNet Airplaneaverage accumulated reward: 0.134 -> 0.120No clear effect
use edge loops for mesh editing instead of per-vertex editing (ablation)Mesh-Agent · ShapeNetIoUImproved

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