{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:W3AI5JRUIPZ7ZGCQCPMUXPRSRX","short_pith_number":"pith:W3AI5JRU","schema_version":"1.0","canonical_sha256":"b6c08ea63443f3fc985013d94bbe328de6001c611b82b59f47c3ed5d5912f3f1","source":{"kind":"arxiv","id":"2606.09825","version":1},"attestation_state":"computed","paper":{"title":"An Agency-Transferring Model-Free Policy Enhancement Technique","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Anton Bolychev, Georgiy Malaniya, Pavel Osinenko, Sinan Ibrahim","submitted_at":"2026-06-08T17:59:39Z","abstract_excerpt":"Training reinforcement learning (RL) policies from scratch is\n  costly: it requires careful reward and environment design,\n  extensive tuning, and substantial computation.\n  Yet many control problems already have a functional but\n  suboptimal policy available as a baseline.\n  This paper proposes a method for embedding such a baseline into\n  the RL training process, simultaneously improving training\n  efficiency relative to from-scratch methods and producing a\n  learning policy that outperforms the baseline.\n  At each step, the method arbitrates between the baseline policy\n  and a trainable lea"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.09825","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T17:59:39Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY","math.OC"],"title_canon_sha256":"038550cd49c34447cde31261f0ff2169d8f6151c8748849d9d995d7429734b84","abstract_canon_sha256":"526168a29acd39313b0d5c9965471933ef02c4f812e75862e10bdf45f4308f58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:12.648624Z","signature_b64":"+bDR+aVeFFwNigFzGt6A8G0KdLmeaAMmxw5LP2uYErAJ4R7F7GfE2WjiYsycQ45jaBF3Jilm/giUs6vX1GssCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6c08ea63443f3fc985013d94bbe328de6001c611b82b59f47c3ed5d5912f3f1","last_reissued_at":"2026-06-09T02:09:12.647788Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:12.647788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Agency-Transferring Model-Free Policy Enhancement Technique","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Anton Bolychev, Georgiy Malaniya, Pavel Osinenko, Sinan Ibrahim","submitted_at":"2026-06-08T17:59:39Z","abstract_excerpt":"Training reinforcement learning (RL) policies from scratch is\n  costly: it requires careful reward and environment design,\n  extensive tuning, and substantial computation.\n  Yet many control problems already have a functional but\n  suboptimal policy available as a baseline.\n  This paper proposes a method for embedding such a baseline into\n  the RL training process, simultaneously improving training\n  efficiency relative to from-scratch methods and producing a\n  learning policy that outperforms the baseline.\n  At each step, the method arbitrates between the baseline policy\n  and a trainable lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09825","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/2606.09825/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.09825","created_at":"2026-06-09T02:09:12.647919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09825v1","created_at":"2026-06-09T02:09:12.647919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09825","created_at":"2026-06-09T02:09:12.647919+00:00"},{"alias_kind":"pith_short_12","alias_value":"W3AI5JRUIPZ7","created_at":"2026-06-09T02:09:12.647919+00:00"},{"alias_kind":"pith_short_16","alias_value":"W3AI5JRUIPZ7ZGCQ","created_at":"2026-06-09T02:09:12.647919+00:00"},{"alias_kind":"pith_short_8","alias_value":"W3AI5JRU","created_at":"2026-06-09T02:09:12.647919+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX","json":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX.json","graph_json":"https://pith.science/api/pith-number/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/graph.json","events_json":"https://pith.science/api/pith-number/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/events.json","paper":"https://pith.science/paper/W3AI5JRU"},"agent_actions":{"view_html":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX","download_json":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX.json","view_paper":"https://pith.science/paper/W3AI5JRU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09825&json=true","fetch_graph":"https://pith.science/api/pith-number/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/graph.json","fetch_events":"https://pith.science/api/pith-number/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/action/storage_attestation","attest_author":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/action/author_attestation","sign_citation":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/action/citation_signature","submit_replication":"https://pith.science/pith/W3AI5JRUIPZ7ZGCQCPMUXPRSRX/action/replication_record"}},"created_at":"2026-06-09T02:09:12.647919+00:00","updated_at":"2026-06-09T02:09:12.647919+00:00"}