#artificial intelligence
May 2026
EfficientTDMPC: Improved MPC Objectives for Sample-Efficient Continuous Control
EfficientTDMPC is introduced, a sample-efficient model-based reinforcement learning method for continuous control built on the TD-MPC family of algorithms that is the new state of the art in sample efficiency on HumanoidBench and the DeepMind Control Suite.
T. Evers, Cristian Meo, Wendelin Böhmer et al.
· arXiv.org · 2 citations