Probabilistic Subgoal Representations for Hierarchical Reinforcement learning

TL;DR

This paper introduces a probabilistic approach to subgoal representation in hierarchical reinforcement learning using Gaussian Processes, enabling better handling of uncertainty and transferability in complex environments.

Contribution

It proposes a novel probabilistic subgoal representation method with learnable kernels, improving adaptability and transfer in HRL over deterministic approaches.

Findings

Outperforms state-of-the-art baselines in standard benchmarks.

Handles stochastic environments effectively.

Shows promising transfer capabilities across tasks.

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.