{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZOBNBVP4MUCMKGIOCCHYL5BGYZ","short_pith_number":"pith:ZOBNBVP4","schema_version":"1.0","canonical_sha256":"cb82d0d5fc6504c5190e108f85f426c67a7b5c3815ff9ceedac92c1357a92b90","source":{"kind":"arxiv","id":"2309.13508","version":2},"attestation_state":"computed","paper":{"title":"Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fang Wang, Haoran Wang, Leya Yang, Siyu Zhang, Yaoru Sun, Yeming Chen, Zeshen Tang","submitted_at":"2023-09-24T00:13:16Z","abstract_excerpt":"Goal-conditioned hierarchical reinforcement learning (HRL) presents a promising approach for enabling effective exploration in complex, long-horizon reinforcement learning (RL) tasks through temporal abstraction. Empirically, heightened inter-level communication and coordination can induce more stable and robust policy improvement in hierarchical systems. Yet, most existing goal-conditioned HRL algorithms have primarily focused on the subgoal discovery, neglecting inter-level cooperation. Here, we propose a goal-conditioned HRL framework named Guided Cooperation via Model-based Rollout (GCMR),"},"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":"2309.13508","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-24T00:13:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8f935aae0a464fa58396e5de137c8acf7e99006d1aee3514bc2c0e4707dc76c7","abstract_canon_sha256":"709cbc95ecb4892bdd22178a3a76200f63ee3ec02db3a08de6281415e4b5b1b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:02.668190Z","signature_b64":"PLJQ5jqiZA/jAuXUG+CpI3tUe5G+KR/ZbT+SEQbyFGzKsd2zZIKO02rnzy26hfOwPyr9mItWcs4Du36stoFzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb82d0d5fc6504c5190e108f85f426c67a7b5c3815ff9ceedac92c1357a92b90","last_reissued_at":"2026-07-05T08:05:02.667673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:02.667673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guided Cooperation in Hierarchical Reinforcement Learning via Model-based Rollout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fang Wang, Haoran Wang, Leya Yang, Siyu Zhang, Yaoru Sun, Yeming Chen, Zeshen Tang","submitted_at":"2023-09-24T00:13:16Z","abstract_excerpt":"Goal-conditioned hierarchical reinforcement learning (HRL) presents a promising approach for enabling effective exploration in complex, long-horizon reinforcement learning (RL) tasks through temporal abstraction. Empirically, heightened inter-level communication and coordination can induce more stable and robust policy improvement in hierarchical systems. Yet, most existing goal-conditioned HRL algorithms have primarily focused on the subgoal discovery, neglecting inter-level cooperation. Here, we propose a goal-conditioned HRL framework named Guided Cooperation via Model-based Rollout (GCMR),"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.13508","kind":"arxiv","version":2},"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/2309.13508/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":"2309.13508","created_at":"2026-07-05T08:05:02.667734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.13508v2","created_at":"2026-07-05T08:05:02.667734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.13508","created_at":"2026-07-05T08:05:02.667734+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZOBNBVP4MUCM","created_at":"2026-07-05T08:05:02.667734+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZOBNBVP4MUCMKGIO","created_at":"2026-07-05T08:05:02.667734+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZOBNBVP4","created_at":"2026-07-05T08:05:02.667734+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/ZOBNBVP4MUCMKGIOCCHYL5BGYZ","json":"https://pith.science/pith/ZOBNBVP4MUCMKGIOCCHYL5BGYZ.json","graph_json":"https://pith.science/api/pith-number/ZOBNBVP4MUCMKGIOCCHYL5BGYZ/graph.json","events_json":"https://pith.science/api/pith-number/ZOBNBVP4MUCMKGIOCCHYL5BGYZ/events.json","paper":"https://pith.science/paper/ZOBNBVP4"},"agent_actions":{"view_html":"https://pith.science/pith/ZOBNBVP4MUCMKGIOCCHYL5BGYZ","download_json":"https://pith.science/pith/ZOBNBVP4MUCMKGIOCCHYL5BGYZ.json","view_paper":"https://pith.science/paper/ZOBNBVP4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.13508&json=true","fetch_graph":"https://pith.science/api/pith-number/ZOBNBVP4MUCMKGIOCCHYL5BGYZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ZOBNBVP4MUCMKGIOCCHYL5BGYZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZOBNBVP4MUCMKGIOCCHYL5BGYZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZOBNBVP4MUCMKGIOCCHYL5BGYZ/action/storage_attestation","attest_author":"https://pith.science/pith/ZOBNBVP4MUCMKGIOCCHYL5BGYZ/action/author_attestation","sign_citation":"https://pith.science/pith/ZOBNBVP4MUCMKGIOCCHYL5BGYZ/action/citation_signature","submit_replication":"https://pith.science/pith/ZOBNBVP4MUCMKGIOCCHYL5BGYZ/action/replication_record"}},"created_at":"2026-07-05T08:05:02.667734+00:00","updated_at":"2026-07-05T08:05:02.667734+00:00"}