Goal Reaching with Eikonal-Constrained Hierarchical Quasimetric Reinforcement Learning
This work addresses goal-reaching tasks in robotics and AI, offering a novel approach with improved generalization, but it is incremental as it builds on existing quasimetric RL methods.
The paper tackles the problem of goal-conditioned reinforcement learning by proposing Eik-HiQRL, a hierarchical method based on an Eikonal PDE reformulation, which achieves state-of-the-art performance in offline navigation and matches temporal-difference methods in manipulation tasks.
Goal-Conditioned Reinforcement Learning (GCRL) mitigates the difficulty of reward design by framing tasks as goal reaching rather than maximizing hand-crafted reward signals. In this setting, the optimal goal-conditioned value function naturally forms a quasimetric, motivating Quasimetric RL (QRL), which constrains value learning to quasimetric mappings and enforces local consistency through discrete, trajectory-based constraints. We propose Eikonal-Constrained Quasimetric RL (Eik-QRL), a continuous-time reformulation of QRL based on the Eikonal Partial Differential Equation (PDE). This PDE-based structure makes Eik-QRL trajectory-free, requiring only sampled states and goals, while improving out-of-distribution generalization. We provide theoretical guarantees for Eik-QRL and identify limitations that arise under complex dynamics. To address these challenges, we introduce Eik-Hierarchical QRL (Eik-HiQRL), which integrates Eik-QRL into a hierarchical decomposition. Empirically, Eik-HiQRL achieves state-of-the-art performance in offline goal-conditioned navigation and yields consistent gains over QRL in manipulation tasks, matching temporal-difference methods.