arXiv Machine Learning By Paul Lutkus, Lars Lindemann, Stephen Tu

Learning Stabilizing Latent Feedback Controllers via Multi-Step Backward Losses

Read the original on arXiv Machine Learning →

arXiv:2610. 40931v1 Announce Type: cross Abstract: Can learned latent dynamics models support the design of feedback controllers that provably stabilize the original system?

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv Machine Learning
Oct 23

Verification of Unknown Dynamical Systems via Autoencoder Latent Space

The paper presents a formal method for verifying high‑dimensional dynamical systems by reducing dimensionality with convex autoencoders and learning latent dynamics via a kernel‑based approach. It constructs a finite abstraction in the latent space that provably contains all true behaviors of the original system, allowing verification results to be mapped back to the original system. Experiments on several systems, including a 26‑dimensional neural‑network‑controlled system, demonstrate significant scalability improvements.

By Robert Reed, Luca Laurenti, Morteza Lahijanian
arXiv Machine Learning
Oct 5

Learning Transferable Policies from Action-free Time Series Through Dynamical Embeddings

The paper introduces a hierarchical model-based reinforcement learning framework that learns control policies from action-free time series by exploiting shared dynamics across related systems. It uses low-dimensional dynamical embeddings to capture both shared structure and individual variation, which then parameterize shared policy and value networks. Experiments on Lorenz-63, double-pendulum, and neural-behavioral data show that these hierarchical policies outperform independently trained ones, achieve higher rewards than planning with the same models, and generalize to unseen systems using only embedding inference.

By Niklas Emonds, Georgia Koppe