Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Probabilistic Programming Bots in Intuitive Physics Game Play
Read the paperCheck 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 |
|---|---|---|---|
| Use CNN-estimated Dirichlet priors instead of uniform priors (ablation) | Probabilistic physics sampling for Flappy Bird · Flappy Bird | average score | Helped |
| Combine CNN-guided sampling with probabilistic physics simulation | Flappy Bird · Flappy Bird | average score | Helped |
| Remove the CNN and use an all-ones Dirichlet prior (ablation) | PB-CNN · Flappy Bird | average score | Hurt |
Closest papers by meaning
- FactorSim: Generative Simulation via Factorized Representation (NeurIPS 2024 · similarity 0.85)
- Explaining Probabilistic Models with Distributional Values (ICML 2024 · similarity 0.84)
- Neurosymbolic Reinforcement Learning: Playing MiniHack with Probabilistic Logic Shields (AAAI 2025 · similarity 0.84)
- Kinetix: Investigating the Training of General Agents through Open-Ended Physics-Based Control Tasks (ICLR 2025 · similarity 0.83)
- I-PHYRE: Interactive Physical Reasoning (ICLR 2024 · similarity 0.83)
- PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors (NeurIPS 2025 · similarity 0.83)
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.