Education
Iterative Feature Matching: Toward Provable Domain Generalization with Logarithmic Environments
To obtain useful guarantees, it is necessary to study data models that encode structure reflective of settings of interest.
05cdc7feee41e3572a9a3f4acb773891-Paper-Conference.pdf
Conversely, the opposite scenario is relatively benign.
GoalReductionwithLoop-RemovalAcceleratesRL andModels HumanBrainActivityinGoal-Directed Learning
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.
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
Beyond existing meta-RL analyses, we provide upper bounds of the expected optimality gap over the task distribution.
