{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4O4D7MDDU2DW6TUPCXOFBT3LFS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a677cf1c1ee105540b917caf06675cb48473ee71cace79816dea7d49ef178457","cross_cats_sorted":["cs.LG","cs.RO","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-12-05T19:31:39Z","title_canon_sha256":"4172af09ab2c327b0112aa1a5324524a384e5fcd4c8348feebc3a8f8eafe8255"},"schema_version":"1.0","source":{"id":"2512.06109","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2512.06109","created_at":"2026-05-18T02:44:32Z"},{"alias_kind":"arxiv_version","alias_value":"2512.06109v3","created_at":"2026-05-18T02:44:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.06109","created_at":"2026-05-18T02:44:32Z"},{"alias_kind":"pith_short_12","alias_value":"4O4D7MDDU2DW","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"4O4D7MDDU2DW6TUP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"4O4D7MDD","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c8faa9f5336067de15e396b637c4a86cc098b8775954378fa8183af1fe5a3dc3","target":"graph","created_at":"2026-05-18T02:44:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"iterating their solutions recovers the original objectives. We further identify a synchronized case of soft-policy RSOC where the policy and transition KL weights coincide, yielding a linear Bellman operator, path-integral solution, and compositionality -- extending these computationally favourable properties to a broad class of control problems."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"the soft-policy formulations majorize the original SOC and RSOC, thus, iterating their solutions recovers the original objectives."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A KL-regularized optimal control umbrella recovers classical SOC and RSOC via iterated soft policies and yields linear Bellman operators with path-integral solutions when policy and transition weights coincide."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A KL-regularized umbrella problem unifies optimal control formulations and recovers the classical objectives through iteration of soft-policy solutions."}],"snapshot_sha256":"e51d1e72361ffddee84c8bc1b10f0312be5f456ab5d61885eea28b19b8fe0dde"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"This paper develops a unified perspective on several optimal control formulations through the lens of Kullback-Leibler (KL) regularization. We propose a central problem that separates the KL penalties on policies and transitions with independent weights, thus generalizing the standard trajectory-level KL-regularization used in probabilistic optimal control. This umbrella formulation recovers various control problems: the classical Stochastic Optimal Control (SOC), Risk-Sensitive Stochastic Optimal Control (RSOC), and their policy-based KL-regularized counterparts, termed soft-policy SOC and RS","authors_text":"Ajinkya Bhole, Guillaume Crevecoeur, Mohammad Mahmoudi Filabadi, Tom Lefebvre","cross_cats":["cs.LG","cs.RO","cs.SY","eess.SY"],"headline":"A KL-regularized umbrella problem unifies optimal control formulations and recovers the classical objectives through iteration of soft-policy solutions.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-12-05T19:31:39Z","title":"Unifying Entropy Regularization in Optimal Control: From and Back to Classical Objectives via Iterated Soft Policies and Path Integral Solutions"},"references":{"count":5,"internal_anchors":1,"resolved_work":5,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Dvijotham, K. and Todorov, E. (2012). Linearly solvable optimal control.Reinforcement learning and approxi- mate dynamic programming for feedback control, 119–","work_id":"c5484cd7-4191-429d-8658-57b7b4a06896","year":2012},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"F¨ ollmer, H. and Schied, A. (2002). Convex measures of risk and trading constraints.Finance and stochastics, 6(4), 429–447. Ito, K. and Kashima, K. (2024). Risk-sensitive control as inference with r´","work_id":"eb194833-26a6-4636-ac2a-65d044a8bf85","year":2002},{"cited_arxiv_id":"1805.00909","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Reinforcement Learning and Control as Probabilistic Inference: Tutorial and Review","work_id":"e29031ac-37fe-4702-86de-bb869d1f5c9a","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Neumann, G. (2011). Variational inference for policy search in changing situations. InInternational confer- ence on machine learning, 817–824. Nishimura, H., Mehr, N., Gaidon, A., and Schwager, M. (20","work_id":"3a495531-8540-40d4-a3e0-5295cac2d83b","year":2011},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Toussaint, M. (2009). Robot trajectory optimization via approximate inference. InInternational conference on machine learning, 1049–1056. Toussaint, M. and Storkey, A. (2006). Probabilistic infer- enc","work_id":"8e5894b3-7799-4db8-bb2e-ea3cff869256","year":2009}],"snapshot_sha256":"38e86502367ed562337676526006ad3aefa916f5f5597a15a692b744f580f399"},"source":{"id":"2512.06109","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-17T00:12:22.323581Z","id":"d946f5c7-c4c7-47ec-9456-05045272207e","model_set":{"reader":"grok-4.3"},"one_line_summary":"A KL-regularized optimal control umbrella recovers classical SOC and RSOC via iterated soft policies and yields linear Bellman operators with path-integral solutions when policy and transition weights coincide.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A KL-regularized umbrella problem unifies optimal control formulations and recovers the classical objectives through iteration of soft-policy solutions.","strongest_claim":"iterating their solutions recovers the original objectives. We further identify a synchronized case of soft-policy RSOC where the policy and transition KL weights coincide, yielding a linear Bellman operator, path-integral solution, and compositionality -- extending these computationally favourable properties to a broad class of control problems.","weakest_assumption":"the soft-policy formulations majorize the original SOC and RSOC, thus, iterating their solutions recovers the original objectives."}},"verdict_id":"d946f5c7-c4c7-47ec-9456-05045272207e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:11ac122f45f048419fe7f0ced0e836b69503e17aae5a9bfd5724a8383730d6fc","target":"record","created_at":"2026-05-18T02:44:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a677cf1c1ee105540b917caf06675cb48473ee71cace79816dea7d49ef178457","cross_cats_sorted":["cs.LG","cs.RO","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2025-12-05T19:31:39Z","title_canon_sha256":"4172af09ab2c327b0112aa1a5324524a384e5fcd4c8348feebc3a8f8eafe8255"},"schema_version":"1.0","source":{"id":"2512.06109","kind":"arxiv","version":3}},"canonical_sha256":"e3b83fb063a6876f4e8f15dc50cf6b2ca8023063510742fc32ab4da1bd610539","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3b83fb063a6876f4e8f15dc50cf6b2ca8023063510742fc32ab4da1bd610539","first_computed_at":"2026-05-18T02:44:32.219957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:32.219957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/C/CeqU4lgfBc2v1mn/C1LeVnsaY29bJBR8uIq7THder/0ezc/uBE0vzaE9y/+QLJgX5xHqn3PL+o/JVWSsABA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:32.220582Z","signed_message":"canonical_sha256_bytes"},"source_id":"2512.06109","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ac122f45f048419fe7f0ced0e836b69503e17aae5a9bfd5724a8383730d6fc","sha256:c8faa9f5336067de15e396b637c4a86cc098b8775954378fa8183af1fe5a3dc3"],"state_sha256":"bf36057aab23e6991dc3d606a8b0a4c2cdd7f6e2a2d807df8d328b716866a44a"}