The pressure for survival prohibits slow, linear adaptation to different goals, i.e., learning value functions from scratch for each new objective. A quick and versatile paradigm is necessary forsuchgoal-directed learning scenarios.

Beyond existing meta-RL analyses, we provide upper bounds of the expected optimality gap over the task distribution.

In online learning problems, exploiting low variance plays an important role in obtaining tight performance guarantees yet ischallenging because variances are often not known a priori. Recently, considerable progress has been made by Zhangetal.

Between 2018 and 2020, the field witnessed asurgein the development of these models (Devlin etal.,2019;Liu