A key element needed in a brain-machine interface (BMI) decoder is the encoding model, which relates the neural activity to intended movement. The vast majority of work have used a representational encoding model, which assumes movement parameters are directly encoded in neural activity. Recent work have in turn suggested the existence of neural dynamics that represent behavior. This recent evidence motivates developing dynamical encoding models with hidden states that encode movement. Regardless of their type, encoding models have vastly characterized a single scale of activity, e.g., either spikes or local field potentials (LFP). In our recent work we developed a multiscale representational encoding model to simultaneously characterize and decode discrete spikes and continuous field activity. However, learning a multiscale dynamical model from simultaneous spike-field recordings in the presence of hidden states is challenging. Here we present an unsupervised learning algorithm for estimating a multiscale state-space model with hidden states and validate it using spike-LFP activity during a reaching movement. We use the learned multiscale statespace model and a corresponding decoder to identify hidden states from spike-LFP activity. We then decode the movement trajectories using these hidden states. We find that the identified states can accurately decode the trajectories. Moreover, we demonstrate that adding LFP to spikes improves the decoding accuracy, suggesting that our unsupervised learning algorithm incorporates information across scales. This learning algorithm could serve as a new tool to study encoding across scales and to enhance future BMI systems.