We develop a framework for model identification adhering to the tenets of neuromorphic computation, without resorting to neural networks as the mathematical substrate. In particular, all computations take place in continuous time. We are naturally led to adaptive observers, where the main technical obstacle is the possible mismatch between the unknown plant order and the observer order. The key concept that informs the proposed framework is an overparameterized model, an input-output equivalent model that provides a suitable parameterization in the overmodeled case, with theoretical extensions also addressing the undermodeled case. A discrete algorithm orchestrates successive experiments to incrementally learn the model order, while a standard parameter adaptation law learns the parameters.

We consider cooperative policy evaluation where agents cannot observe the environment state directly. We propose a fully decentralized belief forming strategy that relies on individual updates and localized interactions over a communication network. Agents exchange both beliefs and value function parameter estimates, allowing information to diffuse over the network. We analytically show that this yields agent parameters with a bounded difference from a centralized baseline.