method · first seen 13 Oct 2026
short-horizon actor-critic
Also: SHAC
First-order reinforcement learning that backpropagates through short simulated rollouts to train actor-critic policies.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Efficient Learning of Differentiable MPC Policies on the GPU via Smoothed ADMM and First-Order Reinforcement LearningPapers · 13 Oct 2026 · Jianghan Zhang, Roland Schwan, Gabriel Bravo-Palacios, John Zhang, Thomas Lew, B…
Latest sources
- Efficient Learning of Differentiable MPC Policies on the GPU via Smoothed ADMM and First-Order Reinforcement LearningPapers · 13 Oct 2026 · Jianghan Zhang, Roland Schwan, Gabriel Bravo-Palacios, John Zhang, Thomas Lew, B…