Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Learning to Paint With Model-Based Deep Reinforcement Learning
Zhewei Huang, Wen Heng, Shuchang Zhou
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use model-based DDPG with a differentiable neural renderer instead of model-free DDPG with PatchQ (ablation) | Learning to Paint agent · CelebA painting | test l2 distance: 5x smaller l2 distance | Improved |
| use model-based DDPG instead of original DDPG (ablation) | Learning to Paint agent · CelebA painting | test l2 distance: 20x smaller l2 distance | Improved |
| add PatchQ patch-level rewards to model-free DDPG critic (ablation) | DDPG · CelebA painting | test performance | Improved |
| use WGAN discriminator reward instead of l2 reward (ablation) | Learning to Paint agent · CelebA painting | test l2 distance | Improved |
| increase number of strokes (100, 200, 400, 1000) (ablation) | Learning to Paint agent · CelebA painting | test loss | Improved |
| use action bundle of 5 strokes per step (ablation) | Learning to Paint agent · CelebA painting | test loss | Improved |
| compare with SPIRAL using 20 opaque strokes | SPIRAL baseline · CelebA painting | test l2 distance: 3x smaller | Improved |
| replace quadratic Bezier strokes with straight strokes, circles or triangles (ablation) | Learning to Paint agent · CelebA painting | painting quality | No clear effect |
Closest papers by meaning
- Paint Transformer: Feed Forward Neural Painting With Stroke Prediction (ICCV 2021 · similarity 0.91)
- Content Masked Loss: Human-Like Brush Stroke Planning in a Reinforcement Learning Painting Agent (AAAI 2021 · similarity 0.88)
- StrokeNet: A Neural Painting Environment (ICLR 2019 · similarity 0.87)
- Neural 3D Strokes: Creating Stylized 3D Scenes with Vectorized 3D Strokes (CVPR 2024 · similarity 0.83)
- Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models (NeurIPS 2026 · similarity 0.82)
- Goal Conditioned Reinforcement Learning for Photo Finishing Tuning (NeurIPS 2024 · similarity 0.82)
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.
