{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3F5ZT6P57GWF4R3T4XBTXCGGDP","short_pith_number":"pith:3F5ZT6P5","schema_version":"1.0","canonical_sha256":"d97b99f9fdf9ac5e4773e5c33b88c61bf53032833f9b9fca22c2d508de24b5d0","source":{"kind":"arxiv","id":"2406.18053","version":1},"attestation_state":"computed","paper":{"title":"Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fuchun Sun, Tianying Ji, Xianyuan Zhan, Yu Luo","submitted_at":"2024-06-26T04:05:04Z","abstract_excerpt":"Hierarchical reinforcement learning (HRL) addresses complex long-horizon tasks by skillfully decomposing them into subgoals. Therefore, the effectiveness of HRL is greatly influenced by subgoal reachability. Typical HRL methods only consider subgoal reachability from the unilateral level, where a dominant level enforces compliance to the subordinate level. However, we observe that when the dominant level becomes trapped in local exploration or generates unattainable subgoals, the subordinate level is negatively affected and cannot follow the dominant level's actions. This can potentially make "},"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":"2406.18053","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T04:05:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9a9e8491984150b624ecb8c11abe08a4971738bf355104d72478574ddccba2ba","abstract_canon_sha256":"6ad906340c334ce3a761b4bd7ca8fbc0248905b21968872dbb9543867a397afa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:54.325167Z","signature_b64":"9HhwC+D1XP9669kbmnQaHRXPKUntYEPOuFvFNYlniFvel7f5HpJJman0WbRXtH1T2JME0NMc/oGE+1mOUdZhDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d97b99f9fdf9ac5e4773e5c33b88c61bf53032833f9b9fca22c2d508de24b5d0","last_reissued_at":"2026-07-05T08:36:54.324532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:54.324532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bidirectional-Reachable Hierarchical Reinforcement Learning with Mutually Responsive Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fuchun Sun, Tianying Ji, Xianyuan Zhan, Yu Luo","submitted_at":"2024-06-26T04:05:04Z","abstract_excerpt":"Hierarchical reinforcement learning (HRL) addresses complex long-horizon tasks by skillfully decomposing them into subgoals. Therefore, the effectiveness of HRL is greatly influenced by subgoal reachability. Typical HRL methods only consider subgoal reachability from the unilateral level, where a dominant level enforces compliance to the subordinate level. However, we observe that when the dominant level becomes trapped in local exploration or generates unattainable subgoals, the subordinate level is negatively affected and cannot follow the dominant level's actions. This can potentially make "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18053","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/2406.18053/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":"2406.18053","created_at":"2026-07-05T08:36:54.324604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18053v1","created_at":"2026-07-05T08:36:54.324604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18053","created_at":"2026-07-05T08:36:54.324604+00:00"},{"alias_kind":"pith_short_12","alias_value":"3F5ZT6P57GWF","created_at":"2026-07-05T08:36:54.324604+00:00"},{"alias_kind":"pith_short_16","alias_value":"3F5ZT6P57GWF4R3T","created_at":"2026-07-05T08:36:54.324604+00:00"},{"alias_kind":"pith_short_8","alias_value":"3F5ZT6P5","created_at":"2026-07-05T08:36:54.324604+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/3F5ZT6P57GWF4R3T4XBTXCGGDP","json":"https://pith.science/pith/3F5ZT6P57GWF4R3T4XBTXCGGDP.json","graph_json":"https://pith.science/api/pith-number/3F5ZT6P57GWF4R3T4XBTXCGGDP/graph.json","events_json":"https://pith.science/api/pith-number/3F5ZT6P57GWF4R3T4XBTXCGGDP/events.json","paper":"https://pith.science/paper/3F5ZT6P5"},"agent_actions":{"view_html":"https://pith.science/pith/3F5ZT6P57GWF4R3T4XBTXCGGDP","download_json":"https://pith.science/pith/3F5ZT6P57GWF4R3T4XBTXCGGDP.json","view_paper":"https://pith.science/paper/3F5ZT6P5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18053&json=true","fetch_graph":"https://pith.science/api/pith-number/3F5ZT6P57GWF4R3T4XBTXCGGDP/graph.json","fetch_events":"https://pith.science/api/pith-number/3F5ZT6P57GWF4R3T4XBTXCGGDP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3F5ZT6P57GWF4R3T4XBTXCGGDP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3F5ZT6P57GWF4R3T4XBTXCGGDP/action/storage_attestation","attest_author":"https://pith.science/pith/3F5ZT6P57GWF4R3T4XBTXCGGDP/action/author_attestation","sign_citation":"https://pith.science/pith/3F5ZT6P57GWF4R3T4XBTXCGGDP/action/citation_signature","submit_replication":"https://pith.science/pith/3F5ZT6P57GWF4R3T4XBTXCGGDP/action/replication_record"}},"created_at":"2026-07-05T08:36:54.324604+00:00","updated_at":"2026-07-05T08:36:54.324604+00:00"}