{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CX3TY33UTIQBBQCA52NBIBPYNY","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":"32335e55e4dff17b92cb6078761504be81ad20031743de62a57ef4314241c66a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T00:10:15Z","title_canon_sha256":"6a085b458548140932b74cba4162622f1b9e9b21781c1e15d3a15c269f663907"},"schema_version":"1.0","source":{"id":"2509.05545","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.05545","created_at":"2026-07-05T12:05:49Z"},{"alias_kind":"arxiv_version","alias_value":"2509.05545v1","created_at":"2026-07-05T12:05:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.05545","created_at":"2026-07-05T12:05:49Z"},{"alias_kind":"pith_short_12","alias_value":"CX3TY33UTIQB","created_at":"2026-07-05T12:05:49Z"},{"alias_kind":"pith_short_16","alias_value":"CX3TY33UTIQBBQCA","created_at":"2026-07-05T12:05:49Z"},{"alias_kind":"pith_short_8","alias_value":"CX3TY33U","created_at":"2026-07-05T12:05:49Z"}],"graph_snapshots":[{"event_id":"sha256:162a6c7c9ee7e134a7a965c0ebd7715284ac3d37eb5021f06791d62cdd6d1e6e","target":"graph","created_at":"2026-07-05T12:05:49Z","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/2509.05545/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Yang Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T00:10:15Z","title":"Reinforcement Learning with Anticipation: A Hierarchical Approach for Long-Horizon Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.05545","kind":"arxiv","version":1},"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":"sha256:653b09d47a494fd1367a4eabd53a3d990a10c7d9c3ab2a0b19fa8c6d35cd1422","target":"record","created_at":"2026-07-05T12:05:49Z","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":"32335e55e4dff17b92cb6078761504be81ad20031743de62a57ef4314241c66a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-06T00:10:15Z","title_canon_sha256":"6a085b458548140932b74cba4162622f1b9e9b21781c1e15d3a15c269f663907"},"schema_version":"1.0","source":{"id":"2509.05545","kind":"arxiv","version":1}},"canonical_sha256":"15f73c6f749a2010c040ee9a1405f86e0d718f8ce514ca156f1cf1a18ed7ed80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"15f73c6f749a2010c040ee9a1405f86e0d718f8ce514ca156f1cf1a18ed7ed80","first_computed_at":"2026-07-05T12:05:49.681002Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:05:49.681002Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QWJnz+vAHZmhf3sYMRI72dupXYGbc40/zF3UXHGXK2ImSL6eatQDdTIkceXhzHEeLOZx37q0EMNxJqNeJqQWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:05:49.681466Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.05545","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:653b09d47a494fd1367a4eabd53a3d990a10c7d9c3ab2a0b19fa8c6d35cd1422","sha256:162a6c7c9ee7e134a7a965c0ebd7715284ac3d37eb5021f06791d62cdd6d1e6e"],"state_sha256":"8cfb0498bd512ec0c041c25b10b70374a8046e07a3e802a56d42a39c4f900c0d"}