SOURCE-LINKED INTELLIGENCE

SUN: Reaching for Novelty in Reinforcement Learning

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

Exploration in reinforcement learning (RL) remains a fundamental challenge. Recent goal-conditioned RL strategies (which select goals to encourage broader state coverage) have shown promising results, but none scores a goal by novelty and reachability jointly: the two signals are traded off by hand, applied in sequence, or one is neglected outright. In this paper, we introduce a reachability-aware goal-selection framework that explicitly integrates these two aspects, and that can be seamlessly incorporated into any off-policy RL algorithm. To this aim, we propose SUccessor-to-Novelty (SUN), an

Read original source ↗ Open in workspace

recordType

paper

region

Global