用单步扩散模型实现快速可控的世界建模，兼顾预测多样性和实时性。
Valdi: Value Diffusion World Models
- 采用单步扩散机制建模不确定动态，支持在线训练与低延迟规划。
- 在CarRacing上性能接近确定性MLP基线，但多模态预测与控制效果存在权衡。
- 适合需要快速响应且需考虑多种可能未来的强化学习任务。
世界模型可支持模型预测控制（MPC），但要求动态预测既足够快以满足在线使用，又具备足够的表达能力来刻画不确定的未来。扩散模型天然适合建模不确定性动态，但其迭代推理过程难以用于低延迟潜在空间规划。本文提出价值扩散世界模型（Valdi），结合端到端在线训练与潜在扩散动态模型，填补这一空白。在CarRacing环境的初步实验中，Valdi在训练和推理阶段均仅使用一步扩散，性能与确定性MLP基线相当。实验揭示了该设置下预测多模态性与控制性能之间的权衡。代码已公开于https://github.com/Kit115/ValueDiffusionWorldModels。
原文摘要 · Abstract (English)
World models can enable Model Predictive Control (MPC), but this requires dynamics prediction that is both fast enough for online use and expressive enough to represent uncertain futures. Diffusion models offer a natural mechanism for modeling uncertain dynamics, yet their iterative inference procedure makes them difficult to use for low-latency latent planning. We bridge this gap with Value Diffusion World Models (Valdi), combining end-to-end online training for MPC with a latent diffusion dynamics model. In preliminary experiments on the CarRacing environment, we show that Valdi, using a single diffusion step at both training and inference, matches a deterministic MLP baseline. Our experiments expose a trade-off between predictive multimodality and control performance in this setup. Code is available at https://github.com/Kit115/ValueDiffusionWorldModels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。