Research

In recent work, we showed that stable formations can emerge through negotiation in a lower-dimensional latent space (which we called geometric embeddings). Appropriately constructed embeddings yield globally stable equilibria based solely on local observations and decisions. We extend this work by applying learning techniques to optimize the geometry of the swarm along the resultant equilibrium manifold. We extend previous work by applying reinforcement learning (RL) to control the orientation of the swarm. In a proof-of-concept, we implem this idea using Continuous Action Learning Automata to learn the optimal orientation (azimuth and altitude angle) of the embedding plane. In this implementation, collective learning is coordinated by a randomly-selected leader agent. ...

In a recent interview with Lex Fridman entitled “Dark Matter of Intelligence and Self-Supervised Learning,” outspoken AI pioneer Yann Lecun suggested the next leap in Artificial Intelligence (AI) will come from learning in lower-dimensional latent spaces. “You don’t predict pixels, you predict an abstract representation of pixels.” - Yann Lecun What does he mean and how is it relevant to the future of AI? Let’s back up and consider the context in which this statement was made. Yann was discussing the limitations of current AI systems, particularly those based on deep neural networks. In a previous article, we touched on one such example — Large Language Models (LLMs). LLMs have demonstrated impressive performance across an array of language-related tasks. So popular, a recent AWS study found a “shocking amount of the web” is already LLM-generated. This is problematic, as LLMs trained on this kind of synthetic content break down and lose their ability to generalize. A recent Nature article described this “model collapse” phenomenon in detail. ...

A fully open architecture implementation of modern multi-agent coordination techniques. All agents make individual decisions based on local information only. There is no global plan. This is an open project I use to explore new ideas, validate theoretical results, and produce data for my academic research. ...