# TD-MPC2: Model-Predictive Reinforcement Learning Control Practice with Latent World Models

- Source: Guyuehome
- Published: 2026-10-17T15:35:00.000Z
- RoboHot: https://robohot.news/en/items/bbzd8nyfxdo1u821jji0oiz8x
- Original: https://www.guyuehome.com/detail?id=2104077729377841154

## Summary

The author uses official pretrained weights to drive a quadruped canine model through real running inference on a local CPU, reconstructing item by item the mathematical construction of the latent world model, the consistency learning objective, symlog two-hot encoding, and MPPI-style sampling-based planning, and records observed phenomena such as planning distribution contraction and the gap between estimates and realized outcomes.