TD-MPC2: Scalable, Robust World Models for Continuous Control

Why is MPC a good tool for this problem? MPC can overcome nonholonomy challenges. It involves planning, not just reactive control. Can generate required ...







Model Predictive Control of Nonholonomic Vehicle Formations
We show that augmenting state representations with intent embeddings generated by an IQL-TD-MPC manager significantly improves off-the-shelf.
IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive ...
TD-MPC is a model-based reinforcement learning (MBRL) algorithm that performs local trajectory optimization in the latent space of a learned implicit ...
TD-MPC2
Extensive experiments demonstrate that the proposed approach improves performance over baselines such as TD-MPC2 by large margins, particularly in 61-DoF.



Autres Cours:

Practical Reinforcement Learning For MPC - Research Collection