Compositional Continual Learning for Open Worlds
This long-term project builds upon our 13-year history of pioneering work in continual and lifelong learning. We’re developing the next generation of continual learning algorithms that acquire and reuse modular skills to solve and zero-shot long-horizon tasks in open-world settings.
Deep representations are likely to be more transferrable for continual learning if they represent reusable cohesive modules within the deep network (Mendez & Eaton, 2023), and so we investigated mechanisms for compositional lifelong learning for both object recognition (Mendez & Eaton, 2021) and RL (Mendez et al., 2022). We showed that lifelong learning using compositional representations dramatically outperforms non-compositional representations, and enables zero-shot generalization to new tasks that are combinations of known modules (Mendez et al., 2022; Hussing et al., 2024). We are currently expanding these compositional representations to develop modular skills that can be dynamically combined, toward the goal of solving long-horizon RL problems. We’re also leveraging ideas for out-of-distribution detection to enable task-agnostic lifelong learning in non-stationary and open-world settings (Gummadi et al., 2022; Gummadi et al., 2024).
