{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CPLI53HRPPA5VUMGAIP3GTYLUN","short_pith_number":"pith:CPLI53HR","schema_version":"1.0","canonical_sha256":"13d68eecf17bc1dad186021fb34f0ba344af2506ceb2600277aab6bb4c803f5a","source":{"kind":"arxiv","id":"2410.07933","version":2},"attestation_state":"computed","paper":{"title":"Offline Hierarchical Reinforcement Learning via Inverse Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Carolin Schmidt, Daniele Gammelli, Filipe Rodrigues, James Harrison, Marco Pavone","submitted_at":"2024-10-10T14:00:21Z","abstract_excerpt":"Hierarchical policies enable strong performance in many sequential decision-making problems, such as those with high-dimensional action spaces, those requiring long-horizon planning, and settings with sparse rewards. However, learning hierarchical policies from static offline datasets presents a significant challenge. Crucially, actions taken by higher-level policies may not be directly observable within hierarchical controllers, and the offline dataset might have been generated using a different policy structure, hindering the use of standard offline learning algorithms. In this work, we prop"},"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":"2410.07933","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T14:00:21Z","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"title_canon_sha256":"669f764adfa6007ac2434ecc4459af3e4761fc204dca82e0bf419bf68dfee145","abstract_canon_sha256":"92ac1617f920e57e987dfeeb1190aa5a0a431b5c30087b9f9e34e1d583b8bbe5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:38.075132Z","signature_b64":"TQ5uXBOKIhT2dRxdQjQuNRwp5YkLbSgtrZ6NXK1cfZdzQmwCzyrU4XfWIhqjmh9ISS615GcltUt1/Fp7b2FXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13d68eecf17bc1dad186021fb34f0ba344af2506ceb2600277aab6bb4c803f5a","last_reissued_at":"2026-07-05T10:33:38.074605Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:38.074605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Hierarchical Reinforcement Learning via Inverse Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SY","eess.SY","math.OC"],"primary_cat":"cs.LG","authors_text":"Carolin Schmidt, Daniele Gammelli, Filipe Rodrigues, James Harrison, Marco Pavone","submitted_at":"2024-10-10T14:00:21Z","abstract_excerpt":"Hierarchical policies enable strong performance in many sequential decision-making problems, such as those with high-dimensional action spaces, those requiring long-horizon planning, and settings with sparse rewards. However, learning hierarchical policies from static offline datasets presents a significant challenge. Crucially, actions taken by higher-level policies may not be directly observable within hierarchical controllers, and the offline dataset might have been generated using a different policy structure, hindering the use of standard offline learning algorithms. In this work, we prop"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07933","kind":"arxiv","version":2},"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/2410.07933/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":"2410.07933","created_at":"2026-07-05T10:33:38.074668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07933v2","created_at":"2026-07-05T10:33:38.074668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07933","created_at":"2026-07-05T10:33:38.074668+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPLI53HRPPA5","created_at":"2026-07-05T10:33:38.074668+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPLI53HRPPA5VUMG","created_at":"2026-07-05T10:33:38.074668+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPLI53HR","created_at":"2026-07-05T10:33:38.074668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28764","citing_title":"Hierarchical Decision Making with Structured Policies: A Principled Design via Inverse Optimization","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPLI53HRPPA5VUMGAIP3GTYLUN","json":"https://pith.science/pith/CPLI53HRPPA5VUMGAIP3GTYLUN.json","graph_json":"https://pith.science/api/pith-number/CPLI53HRPPA5VUMGAIP3GTYLUN/graph.json","events_json":"https://pith.science/api/pith-number/CPLI53HRPPA5VUMGAIP3GTYLUN/events.json","paper":"https://pith.science/paper/CPLI53HR"},"agent_actions":{"view_html":"https://pith.science/pith/CPLI53HRPPA5VUMGAIP3GTYLUN","download_json":"https://pith.science/pith/CPLI53HRPPA5VUMGAIP3GTYLUN.json","view_paper":"https://pith.science/paper/CPLI53HR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07933&json=true","fetch_graph":"https://pith.science/api/pith-number/CPLI53HRPPA5VUMGAIP3GTYLUN/graph.json","fetch_events":"https://pith.science/api/pith-number/CPLI53HRPPA5VUMGAIP3GTYLUN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPLI53HRPPA5VUMGAIP3GTYLUN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPLI53HRPPA5VUMGAIP3GTYLUN/action/storage_attestation","attest_author":"https://pith.science/pith/CPLI53HRPPA5VUMGAIP3GTYLUN/action/author_attestation","sign_citation":"https://pith.science/pith/CPLI53HRPPA5VUMGAIP3GTYLUN/action/citation_signature","submit_replication":"https://pith.science/pith/CPLI53HRPPA5VUMGAIP3GTYLUN/action/replication_record"}},"created_at":"2026-07-05T10:33:38.074668+00:00","updated_at":"2026-07-05T10:33:38.074668+00:00"}