{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QG73PAQQNDAGGRAW7OS52PNLUV","short_pith_number":"pith:QG73PAQQ","schema_version":"1.0","canonical_sha256":"81bfb7821068c0634416fba5dd3daba559c1df1c02a3a010a884a2baa9afe49e","source":{"kind":"arxiv","id":"2607.23726","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Afef Hfaiedh, Giansalvo Cirrincione, Issmail Ellabib, Nahla Khraief, Zahra Abdalla Elashaal","submitted_at":"2026-07-26T15:41:52Z","abstract_excerpt":"Exploration in sparse-reward long-horizon tasks poses significant challenges for reinforcement learning. To address these challenges, we propose a two-level Hierarchical Reinforcement Learning (HRL) framework. The first level handles high-level strategic planning, while the low-level uses the continuous-control Soft Actor-Critic (SAC) algorithm, and they utilize entropy-regularized policy optimization. The proposed framework was trained and evaluated using the Search-and-Rescue-2 (SAR-2) dataset. HRL-SAC effectively addresses sparse-reward long-horizon search problems characterized by delayed "},"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":"2607.23726","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-26T15:41:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c3c82be95debc9987ca04a7ca744e90e5b00095c0f1d842d83cb1b5a1ff85652","abstract_canon_sha256":"71deee7e94c3b44f9a41628fcf3195ee82ab50df45ad8d0b5e0272896d7a3fda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:07.787735Z","signature_b64":"Iom1RnjOUDBl11pOtUh2pHnN84tv1yacufkwGkt4Ex7HVveOPq6pSnzUi+KFsjahLkqVYYQXNNZUQwU55xZ/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81bfb7821068c0634416fba5dd3daba559c1df1c02a3a010a884a2baa9afe49e","last_reissued_at":"2026-07-28T01:23:07.786884Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:07.786884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Afef Hfaiedh, Giansalvo Cirrincione, Issmail Ellabib, Nahla Khraief, Zahra Abdalla Elashaal","submitted_at":"2026-07-26T15:41:52Z","abstract_excerpt":"Exploration in sparse-reward long-horizon tasks poses significant challenges for reinforcement learning. To address these challenges, we propose a two-level Hierarchical Reinforcement Learning (HRL) framework. The first level handles high-level strategic planning, while the low-level uses the continuous-control Soft Actor-Critic (SAC) algorithm, and they utilize entropy-regularized policy optimization. The proposed framework was trained and evaluated using the Search-and-Rescue-2 (SAR-2) dataset. HRL-SAC effectively addresses sparse-reward long-horizon search problems characterized by delayed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23726","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/2607.23726/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":"2607.23726","created_at":"2026-07-28T01:23:07.787322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.23726v1","created_at":"2026-07-28T01:23:07.787322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23726","created_at":"2026-07-28T01:23:07.787322+00:00"},{"alias_kind":"pith_short_12","alias_value":"QG73PAQQNDAG","created_at":"2026-07-28T01:23:07.787322+00:00"},{"alias_kind":"pith_short_16","alias_value":"QG73PAQQNDAGGRAW","created_at":"2026-07-28T01:23:07.787322+00:00"},{"alias_kind":"pith_short_8","alias_value":"QG73PAQQ","created_at":"2026-07-28T01:23:07.787322+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/QG73PAQQNDAGGRAW7OS52PNLUV","json":"https://pith.science/pith/QG73PAQQNDAGGRAW7OS52PNLUV.json","graph_json":"https://pith.science/api/pith-number/QG73PAQQNDAGGRAW7OS52PNLUV/graph.json","events_json":"https://pith.science/api/pith-number/QG73PAQQNDAGGRAW7OS52PNLUV/events.json","paper":"https://pith.science/paper/QG73PAQQ"},"agent_actions":{"view_html":"https://pith.science/pith/QG73PAQQNDAGGRAW7OS52PNLUV","download_json":"https://pith.science/pith/QG73PAQQNDAGGRAW7OS52PNLUV.json","view_paper":"https://pith.science/paper/QG73PAQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.23726&json=true","fetch_graph":"https://pith.science/api/pith-number/QG73PAQQNDAGGRAW7OS52PNLUV/graph.json","fetch_events":"https://pith.science/api/pith-number/QG73PAQQNDAGGRAW7OS52PNLUV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QG73PAQQNDAGGRAW7OS52PNLUV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QG73PAQQNDAGGRAW7OS52PNLUV/action/storage_attestation","attest_author":"https://pith.science/pith/QG73PAQQNDAGGRAW7OS52PNLUV/action/author_attestation","sign_citation":"https://pith.science/pith/QG73PAQQNDAGGRAW7OS52PNLUV/action/citation_signature","submit_replication":"https://pith.science/pith/QG73PAQQNDAGGRAW7OS52PNLUV/action/replication_record"}},"created_at":"2026-07-28T01:23:07.787322+00:00","updated_at":"2026-07-28T01:23:07.787322+00:00"}