In many scientific applications, we observe a system in different conditions in which its components may change, rather than in isolation.

Sutton et al., 2022], is elegantly captured using the options framework [Sutton et al., 1999].

That is, we propose to formulate continual learning as a sequence modeling problem, allowing advanced sequence models to be utilized for continual learning.

This work was done when Mingyu was at MIT.

We demonstrate that this assumption imposes performance limitations in particular on difficult problem instances.

This procedure can leverage noisy, asynchronous human feedback to learn policies with no hand-crafted reward design or exploration bonuses.