Efficient Learning of Differentiable MPC Policies on the GPU via Smoothed ADMM and First-Order Reinforcement Learning
cs.RO, cs.AI, cs.LG
Submitted: 2026-10-13
Updated: 2026-10-13
Code: https://github.com/ToyotaResearchInstitute/turbompc
Terminology
Sources
- Differentiable Nonlinear Model Predictive Control
- On the Differentiability of the Primal-Dual Interior-Point Method
- TurboMPC: Fast, Scalable, and Differentiable Model Predictive Control on the GPU
- First Order Model-Based RL through Decoupled Backpropagation
- Proximal Policy Optimization Algorithms
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation