{"ID":2843165,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.07878","arxiv_id":"2511.07878","title":"Algorithm-Relative Trajectory Valuation in Policy Gradient Control","abstract":"We study how trajectory value depends on the learning algorithm in policy-gradient control. Using Trajectory Shapley in an uncertain LQR, we find a negative correlation between Persistence of Excitation (PE) and marginal value under vanilla REINFORCE ($r\\approx-0.38$). We prove a variance-mediated mechanism: (i) for fixed energy, higher PE yields lower gradient variance; (ii) near saddles, higher variance increases escape probability, raising marginal contribution. When stabilized (state whitening or Fisher preconditioning), this variance channel is neutralized and information content dominates, flipping the correlation positive ($r\\approx+0.29$). Hence, trajectory value is algorithm-relative. Experiments validate the mechanism and show decision-aligned scores (Leave-One-Out) complement Shapley for pruning, while Shapley identifies toxic subsets.","short_abstract":"We study how trajectory value depends on the learning algorithm in policy-gradient control. Using Trajectory Shapley in an uncertain LQR, we find a negative correlation between Persistence of Excitation (PE) and marginal value under vanilla REINFORCE ($r\\approx-0.38$). We prove a variance-mediated mechanism: (i) for fi...","url_abs":"https://arxiv.org/abs/2511.07878","url_pdf":"https://arxiv.org/pdf/2511.07878v1","authors":"[\"Shihao Li\",\"Jiachen Li\",\"Jiamin Xu\",\"Christopher Martin\",\"Wei Li\",\"Dongmei Chen\"]","published":"2025-11-11T06:25:52Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"eess.SY\"]","methods":"[]","has_code":false}