Functional Graphs for Predicting and Explaining Goal Failure in Sparse Goal-Conditioned RL

ArXi:2605.09335v1 Announce Type: new Sparse goal-conditioned reinforcement learning can produce policies whose failures are hidden by aggregate success rates. We analyze trained goal-conditioned value policies through the deterministic functional graphs induced by greedy evaluation: for each goal, every state maps to a single successor, decomposing behavior into attractors and basins. This reveals a local-to-global structure in learned policies. We define local goal (LGS), a one-step statistic measuring the fraction of valid neighboring states whose greedy successor is the goal.