An Optimization Framework for Task Sequencing in Curriculum Learning
This work addresses the challenge of optimizing task sequences in curriculum learning for reinforcement learning agents, offering incremental improvements over existing methods.
The authors tackled the problem of task sequencing in curriculum learning for reinforcement learning by proposing a general optimization framework with different objective functions, and they demonstrated that it can improve initial performance, reduce suboptimal actions, and discover better policies.
Curriculum learning in reinforcement learning is used to shape exploration by presenting the agent with increasingly complex tasks. The idea of curriculum learning has been largely applied in both animal training and pedagogy. In reinforcement learning, all previous task sequencing methods have shaped exploration with the objective of reducing the time to reach a given performance level. We propose novel uses of curriculum learning, which arise from choosing different objective functions. Furthermore, we define a general optimization framework for task sequencing and evaluate the performance of popular metaheuristic search methods on several tasks. We show that curriculum learning can be successfully used to: improve the initial performance, take fewer suboptimal actions during exploration, and discover better policies.