Learning Transferable Policies from Action-free Time Series Through Dynamical Embeddings
Read the original on arXiv Machine Learning →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.
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.