Bradly C Stadie
Assistant Professor of Statistics
- 2006 Sheridan Road, Room 101B
My research explores techniques for developing general machine intelligence. Recently, foundational models such as GPT-3 have provided a promising avenue towards training intelligent machines. In particular, these foundational models show that we can leverage large quantities of unsupervised data to learn a latent underlying structure of a data space. In this latent space, planning and abstract reasoning become much more tractable.
In spite of its promise, there does not currently exist a GPT-3 equivalent in Reinforcement Learning. The current leading method, learning a dynamics model to predict the agent's next state, and then using this model to bootstrap a planning or curiosity module, has proven ineffective. My current research proposes an enticing alternative: that we should use goal-reaching as the foundational model for reinforcement learning. The idea is as follows: we want agents to learn in an unsupervised fashion how to generate and reach various goal states in their environments. We can then bootstrap from this goal-reaching ability, breaking complex goals into a series of simpler tasks. This will endow agents with the ability to plan and reason over long time horizons, an essential capacity for the emergence of general intelligence. There exists a deep relationship between unsupervised goal-reaching and imitation learning, which frequently comes up in my research. From time to time, I also use various tools from graph search, causal inference, and generative networks.
My Google Scholar page can be found here.
My CV is here.