PEAR: Primitive enabled Adaptive Relabeling for boosting Hierarchical Reinforcement Learning

arXiv:2306.06394v5 Announce Type: replace
Abstract: Hierarchical reinforcement learning (HRL) has the potential to solve complex long horizon tasks using temporal abstraction and increased exploration. However, hierarchical agents are difficult to train due to inherent non-stationarity. We present primitive enabled adaptive relabeling (PEAR), a two-phase approach where we first perform adaptive relabeling on a few expert demonstrations to generate efficient subgoal supervision, and then jointly optimize HRL agents by employing reinforcement learning (RL) and imitation learning (IL). We perform theoretical analysis …

abstract abstraction agents arxiv boosting cs.lg exploration hierarchical horizon however reinforcement reinforcement learning solve tasks temporal train type