Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout

arXiv:2309.13508v2 Announce Type: replace
Abstract: Goal-conditioned hierarchical reinforcement learning (HRL) presents a promising approach for enabling effective exploration in complex, long-horizon reinforcement learning (RL) tasks through temporal abstraction. Empirically, heightened inter-level communication and coordination can induce more stable and robust policy improvement in hierarchical systems. Yet, most existing goal-conditioned HRL algorithms have primarily focused on the subgoal discovery, neglecting inter-level cooperation. Here, we propose a goal-conditioned HRL framework named Guided Cooperation via Model-based Rollout (GCMR), aiming to bridge inter-layer information …

abstract abstraction algorithms arxiv communication cs.ai cs.lg enabling exploration hierarchical horizon improvement policy reinforcement reinforcement learning robust systems tasks temporal through type via