{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ERL2FDKFXZWXEIR6LJZUDT5HEN","short_pith_number":"pith:ERL2FDKF","schema_version":"1.0","canonical_sha256":"2457a28d45be6d72223e5a7341cfa7237447e0b1f0a648af3a03caf87be8bec5","source":{"kind":"arxiv","id":"2302.04094","version":1},"attestation_state":"computed","paper":{"title":"Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.RO","authors_text":"Chao Yu, Huazhong Yang, Shiyu Huang, Wei-Wei Tu, Xinyi Yang, Yiwen Sun, Yu Wang, Yuxiang Yang","submitted_at":"2023-02-08T14:44:21Z","abstract_excerpt":"This paper investigates the multi-agent navigation problem, which requires multiple agents to reach the target goals in a limited time. Multi-agent reinforcement learning (MARL) has shown promising results for solving this issue. However, it is inefficient for MARL to directly explore the (nearly) optimal policy in the large search space, which is exacerbated as the agent number increases (e.g., 10+ agents) or the environment is more complex (e.g., 3D simulator). Goal-conditioned hierarchical reinforcement learning (HRL) provides a promising direction to tackle this challenge by introducing a "},"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":"2302.04094","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2023-02-08T14:44:21Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"dca3a24475096650d467ae75bbb4c1f53d698860c74704dd394054b1aaf3d83f","abstract_canon_sha256":"6a33c5ce4dd1504685638a00ef036ed8d31803a4ea4af04dbec13cfc74c449ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:40:00.977511Z","signature_b64":"FQ6WXsvPOFaXnn4SpvZm/JYHUb0BMI9D1dR202VbDqo8w4gTebvwD/QoKCe8m5I+VX6yodWDgAhSFFJ2NzE6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2457a28d45be6d72223e5a7341cfa7237447e0b1f0a648af3a03caf87be8bec5","last_reissued_at":"2026-07-05T05:40:00.977022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:40:00.977022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.RO","authors_text":"Chao Yu, Huazhong Yang, Shiyu Huang, Wei-Wei Tu, Xinyi Yang, Yiwen Sun, Yu Wang, Yuxiang Yang","submitted_at":"2023-02-08T14:44:21Z","abstract_excerpt":"This paper investigates the multi-agent navigation problem, which requires multiple agents to reach the target goals in a limited time. Multi-agent reinforcement learning (MARL) has shown promising results for solving this issue. However, it is inefficient for MARL to directly explore the (nearly) optimal policy in the large search space, which is exacerbated as the agent number increases (e.g., 10+ agents) or the environment is more complex (e.g., 3D simulator). Goal-conditioned hierarchical reinforcement learning (HRL) provides a promising direction to tackle this challenge by introducing a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.04094","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/2302.04094/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":"2302.04094","created_at":"2026-07-05T05:40:00.977079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.04094v1","created_at":"2026-07-05T05:40:00.977079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.04094","created_at":"2026-07-05T05:40:00.977079+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERL2FDKFXZWX","created_at":"2026-07-05T05:40:00.977079+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERL2FDKFXZWXEIR6","created_at":"2026-07-05T05:40:00.977079+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERL2FDKF","created_at":"2026-07-05T05:40:00.977079+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/ERL2FDKFXZWXEIR6LJZUDT5HEN","json":"https://pith.science/pith/ERL2FDKFXZWXEIR6LJZUDT5HEN.json","graph_json":"https://pith.science/api/pith-number/ERL2FDKFXZWXEIR6LJZUDT5HEN/graph.json","events_json":"https://pith.science/api/pith-number/ERL2FDKFXZWXEIR6LJZUDT5HEN/events.json","paper":"https://pith.science/paper/ERL2FDKF"},"agent_actions":{"view_html":"https://pith.science/pith/ERL2FDKFXZWXEIR6LJZUDT5HEN","download_json":"https://pith.science/pith/ERL2FDKFXZWXEIR6LJZUDT5HEN.json","view_paper":"https://pith.science/paper/ERL2FDKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.04094&json=true","fetch_graph":"https://pith.science/api/pith-number/ERL2FDKFXZWXEIR6LJZUDT5HEN/graph.json","fetch_events":"https://pith.science/api/pith-number/ERL2FDKFXZWXEIR6LJZUDT5HEN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERL2FDKFXZWXEIR6LJZUDT5HEN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERL2FDKFXZWXEIR6LJZUDT5HEN/action/storage_attestation","attest_author":"https://pith.science/pith/ERL2FDKFXZWXEIR6LJZUDT5HEN/action/author_attestation","sign_citation":"https://pith.science/pith/ERL2FDKFXZWXEIR6LJZUDT5HEN/action/citation_signature","submit_replication":"https://pith.science/pith/ERL2FDKFXZWXEIR6LJZUDT5HEN/action/replication_record"}},"created_at":"2026-07-05T05:40:00.977079+00:00","updated_at":"2026-07-05T05:40:00.977079+00:00"}