Probabilistic Subgoal Representations for Hierarchical Reinforcement learning
Abstract
In goal-conditioned hierarchical reinforcement learning (HRL), a high-level policy specifies a subgoal for the low-level policy to reach. Effective HRL hinges on a suitable subgoal represen tation function, abstracting state space into latent subgoal space and inducing varied low-level behaviors. Existing methods adopt a subgoal representation that provides a deterministic mapping from state space to latent subgoal space. Instead, this paper utilizes Gaussian Processes (GPs) for the first probabilistic subgoal representation. Our method employs a GP prior on the latent subgoal space to learn a posterior distribution over the subgoal representation functions while exploiting the long-range correlation in the state space through learnable kernels. This enables an adaptive memory that integrates long-range subgoal information from prior planning steps allowing to cope with stochastic uncertainties. Furthermore, we propose a novel learning objective to facilitate the simultaneous learning of probabilistic subgoal representations and policies within a unified framework. In experiments, our approach outperforms state-of-the-art baselines in standard benchmarks but also in environments with stochastic elements and under diverse reward conditions. Additionally, our model shows promising capabilities in transferring low-level policies across different tasks.
Cite
@article{arxiv.2406.16707,
title = {Probabilistic Subgoal Representations for Hierarchical Reinforcement learning},
author = {Vivienne Huiling Wang and Tinghuai Wang and Wenyan Yang and Joni-Kristian Kämäräinen and Joni Pajarinen},
journal= {arXiv preprint arXiv:2406.16707},
year = {2024}
}