{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CPLI53HRPPA5VUMGAIP3GTYLUN","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":"92ac1617f920e57e987dfeeb1190aa5a0a431b5c30087b9f9e34e1d583b8bbe5","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T14:00:21Z","title_canon_sha256":"669f764adfa6007ac2434ecc4459af3e4761fc204dca82e0bf419bf68dfee145"},"schema_version":"1.0","source":{"id":"2410.07933","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07933","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07933v2","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07933","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"pith_short_12","alias_value":"CPLI53HRPPA5","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"pith_short_16","alias_value":"CPLI53HRPPA5VUMG","created_at":"2026-07-05T10:33:38Z"},{"alias_kind":"pith_short_8","alias_value":"CPLI53HR","created_at":"2026-07-05T10:33:38Z"}],"graph_snapshots":[{"event_id":"sha256:a25f0e48b1a92fd272875499eb47a592d87b86d4b6dc90963c7a212699e3fdb5","target":"graph","created_at":"2026-07-05T10:33:38Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.07933/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Carolin Schmidt, Daniele Gammelli, Filipe Rodrigues, James Harrison, Marco Pavone","cross_cats":["cs.SY","eess.SY","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T14:00:21Z","title":"Offline Hierarchical Reinforcement Learning via Inverse Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07933","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ae8337b269b62865a7a8fa6bccb3e356206a868281cb69300a1ca4e703dbabf0","target":"record","created_at":"2026-07-05T10:33:38Z","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":"92ac1617f920e57e987dfeeb1190aa5a0a431b5c30087b9f9e34e1d583b8bbe5","cross_cats_sorted":["cs.SY","eess.SY","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-10T14:00:21Z","title_canon_sha256":"669f764adfa6007ac2434ecc4459af3e4761fc204dca82e0bf419bf68dfee145"},"schema_version":"1.0","source":{"id":"2410.07933","kind":"arxiv","version":2}},"canonical_sha256":"13d68eecf17bc1dad186021fb34f0ba344af2506ceb2600277aab6bb4c803f5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"13d68eecf17bc1dad186021fb34f0ba344af2506ceb2600277aab6bb4c803f5a","first_computed_at":"2026-07-05T10:33:38.074605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:33:38.074605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TQ5uXBOKIhT2dRxdQjQuNRwp5YkLbSgtrZ6NXK1cfZdzQmwCzyrU4XfWIhqjmh9ISS615GcltUt1/Fp7b2FXDw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:33:38.075132Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07933","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae8337b269b62865a7a8fa6bccb3e356206a868281cb69300a1ca4e703dbabf0","sha256:a25f0e48b1a92fd272875499eb47a592d87b86d4b6dc90963c7a212699e3fdb5"],"state_sha256":"cbc63fa8419a16ee9ad15b966315310161ef2a53cdf5f5117fee76a9d297a848"}