{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:I5REZLIRD7WBBD66JJWZ6ZM2GX","short_pith_number":"pith:I5REZLIR","schema_version":"1.0","canonical_sha256":"47624cad111fec108fde4a6d9f659a35e807aea7b268ec81fbb251256e6b6ac3","source":{"kind":"arxiv","id":"2202.01511","version":3},"attestation_state":"computed","paper":{"title":"Challenging Common Assumptions in Convex Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Marcello Restelli, Mirco Mutti, Piersilvio De Bartolomeis, Riccardo De Santi","submitted_at":"2022-02-03T10:47:10Z","abstract_excerpt":"The classic Reinforcement Learning (RL) formulation concerns the maximization of a scalar reward function. More recently, convex RL has been introduced to extend the RL formulation to all the objectives that are convex functions of the state distribution induced by a policy. Notably, convex RL covers several relevant applications that do not fall into the scalar formulation, including imitation learning, risk-averse RL, and pure exploration. In classic RL, it is common to optimize an infinite trials objective, which accounts for the state distribution instead of the empirical state visitation "},"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":"2202.01511","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-03T10:47:10Z","cross_cats_sorted":[],"title_canon_sha256":"bbb41df82ae6214eb90bf9461565b854c5e2617e13311d03c5b8fb81af28e611","abstract_canon_sha256":"87774645f03df3bffb74be521ff757908ef180599f2c1a83dc5ac66618925388"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:15.588671Z","signature_b64":"1t62sHogf3Xc+1i/UX1lzBOLMnQEbTfOI7eqbrwm5HDDbY6uTErPtDZ2gZTK01SZtcA9fouNQPlsuWeZx8GZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47624cad111fec108fde4a6d9f659a35e807aea7b268ec81fbb251256e6b6ac3","last_reissued_at":"2026-07-05T05:36:15.588174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:15.588174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Challenging Common Assumptions in Convex Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Marcello Restelli, Mirco Mutti, Piersilvio De Bartolomeis, Riccardo De Santi","submitted_at":"2022-02-03T10:47:10Z","abstract_excerpt":"The classic Reinforcement Learning (RL) formulation concerns the maximization of a scalar reward function. More recently, convex RL has been introduced to extend the RL formulation to all the objectives that are convex functions of the state distribution induced by a policy. Notably, convex RL covers several relevant applications that do not fall into the scalar formulation, including imitation learning, risk-averse RL, and pure exploration. In classic RL, it is common to optimize an infinite trials objective, which accounts for the state distribution instead of the empirical state visitation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.01511","kind":"arxiv","version":3},"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/2202.01511/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":"2202.01511","created_at":"2026-07-05T05:36:15.588233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.01511v3","created_at":"2026-07-05T05:36:15.588233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.01511","created_at":"2026-07-05T05:36:15.588233+00:00"},{"alias_kind":"pith_short_12","alias_value":"I5REZLIRD7WB","created_at":"2026-07-05T05:36:15.588233+00:00"},{"alias_kind":"pith_short_16","alias_value":"I5REZLIRD7WBBD66","created_at":"2026-07-05T05:36:15.588233+00:00"},{"alias_kind":"pith_short_8","alias_value":"I5REZLIR","created_at":"2026-07-05T05:36:15.588233+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.01432","citing_title":"The Geometry of Nonlinear Reinforcement Learning","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I5REZLIRD7WBBD66JJWZ6ZM2GX","json":"https://pith.science/pith/I5REZLIRD7WBBD66JJWZ6ZM2GX.json","graph_json":"https://pith.science/api/pith-number/I5REZLIRD7WBBD66JJWZ6ZM2GX/graph.json","events_json":"https://pith.science/api/pith-number/I5REZLIRD7WBBD66JJWZ6ZM2GX/events.json","paper":"https://pith.science/paper/I5REZLIR"},"agent_actions":{"view_html":"https://pith.science/pith/I5REZLIRD7WBBD66JJWZ6ZM2GX","download_json":"https://pith.science/pith/I5REZLIRD7WBBD66JJWZ6ZM2GX.json","view_paper":"https://pith.science/paper/I5REZLIR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.01511&json=true","fetch_graph":"https://pith.science/api/pith-number/I5REZLIRD7WBBD66JJWZ6ZM2GX/graph.json","fetch_events":"https://pith.science/api/pith-number/I5REZLIRD7WBBD66JJWZ6ZM2GX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I5REZLIRD7WBBD66JJWZ6ZM2GX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I5REZLIRD7WBBD66JJWZ6ZM2GX/action/storage_attestation","attest_author":"https://pith.science/pith/I5REZLIRD7WBBD66JJWZ6ZM2GX/action/author_attestation","sign_citation":"https://pith.science/pith/I5REZLIRD7WBBD66JJWZ6ZM2GX/action/citation_signature","submit_replication":"https://pith.science/pith/I5REZLIRD7WBBD66JJWZ6ZM2GX/action/replication_record"}},"created_at":"2026-07-05T05:36:15.588233+00:00","updated_at":"2026-07-05T05:36:15.588233+00:00"}