Jesse Read

Transforming sensor data into geometric attractors reveals early signs of robot degradation that traditional deep learning methods miss.

Decoupling communication from policy in MARL lets you drastically reduce bandwidth needs without sacrificing performance, opening the door to real-world deployments with drone swarms and other bandwidth-limited systems.

Turns out, even with fancy self-supervised learning, traditional Bayesian filters are still tough to beat for turbofan engine health estimation, suggesting we're missing something fundamental about this inverse problem.