Problem
Research questions and friction points this paper is trying to address.
latent world model
decoder
free-running rollout
reconstruction error
Rollout-Decoded Reconstruction for Long-Horizon Prediction in Latent World Models
🤖 AI Summary
研究通过Rollout-Decoded Reconstruction方法，在混沌系统中提高了长期预测的准确性，通过在训练时引入自由运行模型并惩罚重建误差来解决预测差距问题。
📝 Abstract
A latent world model trains its decoder on latents anchored to observations, then deploys it on the model's own free-running rollout, hundreds of steps past the last observation. Rollout-Decoded Reconstruction (RDR) closes this gap with a single loss term that free-runs the model during training exactly as evaluation will, decodes every rollout latent, and penalizes reconstruction error against ground truth. The term adds no parameters, costs training-time compute only, and reduces to the standard objective at weight zero, so every comparison in this paper is a one-flag A/B. On the chaotic Kuramoto-Sivashinsky equation, RDR raises valid prediction time (the time to first crossing of normalized error 0.5) from $3.87 \pm 0.23$ to $6.97 \pm 0.42$ time units at an identical 193,568 parameters, a $1.80\times$ improvement confirmed on seeds never used in selection and holding in 10 of 10 preregistered configurations at ratios of 1.71-2.50$\times$. The results come from a single system; a sweep in which the advantage grows with latent width is descriptive, and control experiments on two classic tasks are preliminary.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Rollout-Decoded Reconstruction
latent world models
long-horizon prediction
free-running rollout
🔎 Similar Papers
No similar papers found.
