{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CX3TY33UTIQBBQCA52NBIBPYNY","short_pith_number":"pith:CX3TY33U","schema_version":"1.0","canonical_sha256":"15f73c6f749a2010c040ee9a1405f86e0d718f8ce514ca156f1cf1a18ed7ed80","source":{"kind":"arxiv","id":"2509.05545","version":1},"attestation_state":"computed","paper":{"title":"Reinforcement Learning with Anticipation: A Hierarchical Approach for Long-Horizon Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yang Yu","submitted_at":"2025-09-06T00:10:15Z","abstract_excerpt":"Solving long-horizon goal-conditioned tasks remains a significant challenge in reinforcement learning (RL). Hierarchical reinforcement learning (HRL) addresses this by decomposing tasks into more manageable sub-tasks, but the automatic discovery of the hierarchy and the joint training of multi-level policies often suffer from instability and can lack theoretical guarantees. In this paper, we introduce Reinforcement Learning with Anticipation (RLA), a principled and potentially scalable framework designed to address these limitations. The RLA agent learns two synergistic models: a low-level, go"},"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":"2509.05545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T00:10:15Z","cross_cats_sorted":[],"title_canon_sha256":"6a085b458548140932b74cba4162622f1b9e9b21781c1e15d3a15c269f663907","abstract_canon_sha256":"32335e55e4dff17b92cb6078761504be81ad20031743de62a57ef4314241c66a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:49.681466Z","signature_b64":"QWJnz+vAHZmhf3sYMRI72dupXYGbc40/zF3UXHGXK2ImSL6eatQDdTIkceXhzHEeLOZx37q0EMNxJqNeJqQWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15f73c6f749a2010c040ee9a1405f86e0d718f8ce514ca156f1cf1a18ed7ed80","last_reissued_at":"2026-07-05T12:05:49.681002Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:49.681002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Anticipation: A Hierarchical Approach for Long-Horizon Tasks","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Yang Yu","submitted_at":"2025-09-06T00:10:15Z","abstract_excerpt":"Solving long-horizon goal-conditioned tasks remains a significant challenge in reinforcement learning (RL). Hierarchical reinforcement learning (HRL) addresses this by decomposing tasks into more manageable sub-tasks, but the automatic discovery of the hierarchy and the joint training of multi-level policies often suffer from instability and can lack theoretical guarantees. In this paper, we introduce Reinforcement Learning with Anticipation (RLA), a principled and potentially scalable framework designed to address these limitations. The RLA agent learns two synergistic models: a low-level, go"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05545","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/2509.05545/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":"2509.05545","created_at":"2026-07-05T12:05:49.681055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.05545v1","created_at":"2026-07-05T12:05:49.681055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05545","created_at":"2026-07-05T12:05:49.681055+00:00"},{"alias_kind":"pith_short_12","alias_value":"CX3TY33UTIQB","created_at":"2026-07-05T12:05:49.681055+00:00"},{"alias_kind":"pith_short_16","alias_value":"CX3TY33UTIQBBQCA","created_at":"2026-07-05T12:05:49.681055+00:00"},{"alias_kind":"pith_short_8","alias_value":"CX3TY33U","created_at":"2026-07-05T12:05:49.681055+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/CX3TY33UTIQBBQCA52NBIBPYNY","json":"https://pith.science/pith/CX3TY33UTIQBBQCA52NBIBPYNY.json","graph_json":"https://pith.science/api/pith-number/CX3TY33UTIQBBQCA52NBIBPYNY/graph.json","events_json":"https://pith.science/api/pith-number/CX3TY33UTIQBBQCA52NBIBPYNY/events.json","paper":"https://pith.science/paper/CX3TY33U"},"agent_actions":{"view_html":"https://pith.science/pith/CX3TY33UTIQBBQCA52NBIBPYNY","download_json":"https://pith.science/pith/CX3TY33UTIQBBQCA52NBIBPYNY.json","view_paper":"https://pith.science/paper/CX3TY33U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.05545&json=true","fetch_graph":"https://pith.science/api/pith-number/CX3TY33UTIQBBQCA52NBIBPYNY/graph.json","fetch_events":"https://pith.science/api/pith-number/CX3TY33UTIQBBQCA52NBIBPYNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CX3TY33UTIQBBQCA52NBIBPYNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CX3TY33UTIQBBQCA52NBIBPYNY/action/storage_attestation","attest_author":"https://pith.science/pith/CX3TY33UTIQBBQCA52NBIBPYNY/action/author_attestation","sign_citation":"https://pith.science/pith/CX3TY33UTIQBBQCA52NBIBPYNY/action/citation_signature","submit_replication":"https://pith.science/pith/CX3TY33UTIQBBQCA52NBIBPYNY/action/replication_record"}},"created_at":"2026-07-05T12:05:49.681055+00:00","updated_at":"2026-07-05T12:05:49.681055+00:00"}