model predictive control
Model predictive control is a planning strategy where a controller simulates the future outcomes of different action sequences using a model of the system. It picks the best first action, executes it, then repeats the entire simulation from the new state. This receding horizon approach allows flexible reactions to change guided by predicted future states.
The papers share a focus on how to build the model used for control. One combines the approach with reinforcement learning to handle whole-body balance. Another uses a world model trained on autonomously collected play data to enable dexterous manipulation. A third directly fixes a failure of standard world models to represent action consequences. Together, they show that the quality of the learned model is the decisive factor for success in complex applications.
- Papers
- 5
- Released code
- 0
- First seen
- Sept 2026
- Latest
- Nov 2026
5 papers in the last two months, against 0 in the two before.
Start here
Two papers to read first, in the order they came out- 1HULK teaches humanoids to carry heavy loads while staying balanced
HULK uses model predictive control to guide reinforcement learning for humanoid whole-body forceful loco-manipulation under sustained payloads.
Oct 2026 - 2Minutes of supervised play bootstrap hours of autonomous robot practice
A robot learns dexterous manipulation by mimicking minutes of human play, then autonomously practices to train a world model and guide control.
Oct 2026
How fast it is moving
Often studied with
on-policy distillationA training method where a student model learns from a teacher using its own current policy's outputs, often improving reasoning and instruction following.2 togetherlatent world modelA learned internal, compressed representation of environment dynamics, enabling future-aware planning, generation, and reasoning directly in latent space.2 togetherjoint-embedding predictive architectureAn encoder predicts the latent representation of future data points from current and past observations, bypassing pixel-level reconstruction.2 togetherThe papers
Most central to this idea first, not most recent.
- Big Techcs.RO
Minutes of supervised play bootstrap hours of autonomous robot practice
A robot learns dexterous manipulation by mimicking minutes of human play, then autonomously practices to train a world model and guide control.
Amazon Frontier AI & Robotics (FAR), University of Maryland, College Park · Oct 2026
- Big Techcs.RO
HULK teaches humanoids to carry heavy loads while staying balanced
HULK uses model predictive control to guide reinforcement learning for humanoid whole-body forceful loco-manipulation under sustained payloads.
University of Michigan, University of California, Los Angeles · Oct 2026
- Academiccs.RO
Searching harder against learned rewards can halve a robot's true performance
Planning harder against a learned reward often destroys true performance, but calibrated temperature can limit the damage.
The University of Texas at Austin · Nov 2026
- Research Labcs.LG
World models learn true dynamics with fewer parameters
World2vec learns faithful, compact world models from observations and actions without rewards, matching reward-trained control and identifying dynamical systems.
Helmholtz Munich, Munich Center for Machine Learning (MCML) · Oct 2026
- Top University
Action-discriminative world models improve counterfactual planning for robot control
World models for planning should preserve action-dependent differences for counterfactual selection, not just factual prediction accuracy.
Nanjing University · Sept 2026
Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.