{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V56ZQ5PWIPMYDUEPKIEYFYEHAW","short_pith_number":"pith:V56ZQ5PW","schema_version":"1.0","canonical_sha256":"af7d9875f643d981d08f520982e08705a78ee60f1eed2e696ad1da1657befe87","source":{"kind":"arxiv","id":"2506.21039","version":3},"attestation_state":"computed","paper":{"title":"Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jaebak Hwang, Jeongmo Kim, Sanghyeon Lee, Seungyul Han","submitted_at":"2025-06-26T06:35:42Z","abstract_excerpt":"Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are sparse. While hierarchical and graph-based methods offer partial solutions, their reliance on conventional hindsight relabeling often fails to correct subgoal infeasibility, leading to inefficient high-level planning. To address this, we propose Strict Subgoal Execution (SSE), a graph-based hierarchical RL framework that integrates Frontier Experience Replay (FER) to separate unreachable from admissible subgoals and streamline high-level decision "},"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":"2506.21039","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:35:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"95ec10578d5f6af63c8257d3c4ed09438646c90e0b6319e980615db5a2547e25","abstract_canon_sha256":"fa709003b23e041626a2a5347bd66ee183659c3a16c3537905db781670266398"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:14.934681Z","signature_b64":"QwSPOzuePE91JdxrlUWkkI7CMz3RpIjZUC28SOxR/Cw/Lf6ZAVir6p66O2zeq9WVIQAVMHGrbrxV0d7KjK/eCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af7d9875f643d981d08f520982e08705a78ee60f1eed2e696ad1da1657befe87","last_reissued_at":"2026-05-21T01:04:14.933769Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:14.933769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strict Subgoal Execution: Reliable Long-Horizon Planning in Hierarchical Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jaebak Hwang, Jeongmo Kim, Sanghyeon Lee, Seungyul Han","submitted_at":"2025-06-26T06:35:42Z","abstract_excerpt":"Long-horizon goal-conditioned tasks pose fundamental challenges for reinforcement learning (RL), particularly when goals are distant and rewards are sparse. While hierarchical and graph-based methods offer partial solutions, their reliance on conventional hindsight relabeling often fails to correct subgoal infeasibility, leading to inefficient high-level planning. To address this, we propose Strict Subgoal Execution (SSE), a graph-based hierarchical RL framework that integrates Frontier Experience Replay (FER) to separate unreachable from admissible subgoals and streamline high-level decision "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21039","kind":"arxiv","version":3},"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/2506.21039/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":"2506.21039","created_at":"2026-05-21T01:04:14.933903+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21039v3","created_at":"2026-05-21T01:04:14.933903+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21039","created_at":"2026-05-21T01:04:14.933903+00:00"},{"alias_kind":"pith_short_12","alias_value":"V56ZQ5PWIPMY","created_at":"2026-05-21T01:04:14.933903+00:00"},{"alias_kind":"pith_short_16","alias_value":"V56ZQ5PWIPMYDUEP","created_at":"2026-05-21T01:04:14.933903+00:00"},{"alias_kind":"pith_short_8","alias_value":"V56ZQ5PW","created_at":"2026-05-21T01:04:14.933903+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/V56ZQ5PWIPMYDUEPKIEYFYEHAW","json":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW.json","graph_json":"https://pith.science/api/pith-number/V56ZQ5PWIPMYDUEPKIEYFYEHAW/graph.json","events_json":"https://pith.science/api/pith-number/V56ZQ5PWIPMYDUEPKIEYFYEHAW/events.json","paper":"https://pith.science/paper/V56ZQ5PW"},"agent_actions":{"view_html":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW","download_json":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW.json","view_paper":"https://pith.science/paper/V56ZQ5PW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21039&json=true","fetch_graph":"https://pith.science/api/pith-number/V56ZQ5PWIPMYDUEPKIEYFYEHAW/graph.json","fetch_events":"https://pith.science/api/pith-number/V56ZQ5PWIPMYDUEPKIEYFYEHAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/action/storage_attestation","attest_author":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/action/author_attestation","sign_citation":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/action/citation_signature","submit_replication":"https://pith.science/pith/V56ZQ5PWIPMYDUEPKIEYFYEHAW/action/replication_record"}},"created_at":"2026-05-21T01:04:14.933903+00:00","updated_at":"2026-05-21T01:04:14.933903+00:00"}