Research
Learning Goal-Reaching Quasimetric Geometry From Finite-Time Reachability
arXiv:2610.00778v1 Announce Type: new Abstract: In goal-conditioned reinforcement learning (GCRL), quasimetric learning models goal-reaching costs as quasimetric distances, connecting local constraint
arXiv:2610.00778v1 Announce Type: new Abstract: In goal-conditioned reinforcement learning (GCRL), quasimetric learning models goal-reaching costs as quasimetric distances, connecting local constraints to global value geometry. Its local constraints, however, should reflect the direction- dependent effects of control composition over a finite horizon together with environmental feasibility. We propose ReQRL, which constrains the critic's value gradients through finite-horizon reachability. Drawing on state-constrained optimal control, we decouple dynamical reachability from boundary geometry, estimating both from data. On OGBench, our method outperforms or rivals existing quasimetric approaches and other offline GCRL methods.
Related
- Mollified Value Learning
- Adaptive Coarse-to-Fine Subgoal Refinement for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
- Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL
- Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal-Conditioned Control
Source: arXiv cs.LG | 2026-10-02