Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Learning to Simulate Dynamic Environments With GameGAN
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add the memory module and disentangling rendering engine to GameGAN-M (ablation) | GameGAN · Pacman | mean score: 1.99 $\pm$ 2.23 -> 1.13 $\pm$ 1.56 | Hurt |
| Add the memory module and disentangling rendering engine to GameGAN-M (ablation) | GameGAN · VizDoom | mean score: 724 $\pm$ 468 -> 765 $\pm$ 482 | Helped |
| Add the memory module for long-term consistency (ablation) | GameGAN · Pacman-Maze come-back-home task | wall-state distance | Helped |
| Add a small reconstruction loss in image and feature spaces | GameGAN · Pacman and VizDoom | training stability | Helped |
Closest papers by meaning
- Diffusion Models Are Real-Time Game Engines (ICLR 2025 · similarity 0.88)
- Learning Interactive Real-World Simulators (ICLR 2024 · similarity 0.88)
- FactorSim: Generative Simulation via Factorized Representation (NeurIPS 2024 · similarity 0.86)
- Exploration-Driven Generative Interactive Environments (CVPR 2025 · similarity 0.85)
- SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning (NeurIPS 2026 · similarity 0.85)
- From Zero to Hero: Training-Free Custom Concept Spawning in World Models (NeurIPS 2026 · similarity 0.85)
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.