AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Brick-by-Brick: Combinatorial Construction with Deep Reinforcement Learning

Hyunsoo Chung, Jungtaek Kim, Boris Knyazev, Jinhwi Lee, Graham W. Taylor, Jaesik Park, Minsu Cho

NeurIPS 2021 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 10 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
Use the pretrained validity prediction network instead of the jointly trained network (ablation)Brick-by-Brick action validity prediction · Action validity prediction test set, pivotprecision: 0.9809 -> 0.9909Improved
Use the pretrained validity prediction network instead of the jointly trained network (ablation)Brick-by-Brick action validity prediction · Action validity prediction test set, offsetprecision: 0.8674 -> 0.9125Improved
Add node features to the validity prediction GNN (ablation)Brick-by-Brick action validity prediction · Action validity prediction test set, offsetprecision: 0.7931 -> 0.9125Improved
Add edge features to the validity prediction GNN (ablation)Brick-by-Brick action validity prediction · Action validity prediction test set, offsetprecision: 0.8897 -> 0.9125Improved
Use a GNN instead of an MLP for action validity predictionBrick-by-Brick action validity prediction · Action validity prediction test set, offsetprecision: 0.5130 -> 0.9125Improved
Use graph message passing rather than independent MLP brick features (ablation)Brick-by-Brick construction · Randomly-assembled object constructionepisode returnNo clear effect
Use reinforcement learning rather than sequence-level supervised learningBrick-by-Brick construction · Randomly-assembled object construction test setgeneralization to unseen imagesImproved
Use image-conditioned Brick-by-Brick instead of Bayesian optimizationBrick-by-Brick construction · ModelNet constructionepisode returnImproved

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