{"paper":{"title":"Non-Convex Sparse Reinforcement Learning via Non-Monotone Inclusions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kyohei Suzuki, onstantinos Slavakis","submitted_at":"2026-07-06T12:25:47Z","abstract_excerpt":"This work delivers two key contributions: one to efficient feature selection in reinforcement learning\n  (RL), the other to the theory of non-monotone inclusions. On the RL side, the estimation bias inherent\n  in conventional regularization schemes is addressed by augmenting classical least-squares\n  temporal-difference (LSTD) policy evaluation with the sparsity-inducing, non-convex projected minimax\n  concave (PMC) penalty. Because the PMC penalty is weakly convex, the resulting fixed-point problem is\n  no longer monotone; instead, it falls under a broader class of non-monotone inclusions inv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04990","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.04990/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}