CRISP: Curriculum inducing Primitive Informed Subgoal Prediction

arXiv:2304.03535v4 Announce Type: replace
Abstract: Hierarchical reinforcement learning (HRL) is a promising approach that uses temporal abstraction to solve complex long horizon problems. However, simultaneously learning a hierarchy of policies is unstable as it is challenging to train higher-level policy when the lower-level primitive is non-stationary. In this paper, we present CRISP, a novel HRL algorithm that effectively generates a curriculum of achievable subgoals for evolving lower-level primitives using reinforcement learning and imitation learning. CRISP uses the lower level primitive …

abstract abstraction arxiv cs.lg curriculum hierarchical horizon however paper policies policy prediction reinforcement reinforcement learning solve temporal train type