A central goal of artificial intelligence in high-stakes decision-making applications is to
design a single algorithm that simultaneously expresses generalizability by learning …

This review presents a modern perspective on dynamical systems in the context of current
goals and open challenges. In particular, our review focuses on the key challenges of …

We introduce a new class of time-continuous recurrent neural network models. Instead of
declaring a learning system's dynamics by implicit nonlinearities, we construct networks of …

A proper parametrization of state transition matrices of linear state-space models (SSMs)
followed by standard nonlinearities enables them to efficiently learn representations from …

Continuous-time neural networks are a class of machine learning systems that can tackle
representation learning on spatiotemporal decision-making tasks. These models are …

Recurrent neural networks (RNNs) with continuous-time hidden states are a natural fit for
modeling irregularly-sampled time series. These models, however, face difficulties when the …

Physics-informed machine learning (PIML) is a set of methods and tools that systematically
integrate machine learning (ML) algorithms with physical constraints and abstract …

Multi-agent reinforcement learning (MARL) research is faced with a trade-off: it either uses
complex environments requiring large compute resources, which makes it inaccessible to …

Imitation learning enables high-fidelity, vision-based learning of policies within rich,
photorealistic environments. However, such techniques often rely on traditional discrete-time …

World models learn behaviors in a latent imagination space to enhance the sample-
efficiency of deep reinforcement learning (RL) algorithms. While learning world models for …