{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OIWT7JDC5VVFEOVG7PUMUUWRSJ","short_pith_number":"pith:OIWT7JDC","schema_version":"1.0","canonical_sha256":"722d3fa462ed6a523aa6fbe8ca52d19245690ff918755fd5e3846fcdab256976","source":{"kind":"arxiv","id":"1807.05424","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Reinforcement Learning Framework towards Multi-agent Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.RO","authors_text":"Huihuan Qian, Shuaijun Li, Wenhao Ding","submitted_at":"2018-07-14T18:07:32Z","abstract_excerpt":"In this paper, we propose a navigation algorithm oriented to multi-agent environment. This algorithm is expressed as a hierarchical framework that contains a Hidden Markov Model (HMM) and a Deep Reinforcement Learning (DRL) structure. For simplification, we term our method Hierarchical Navigation Reinforcement Network (HNRN). In high- level architecture, we train an HMM to evaluate the agent's perception to obtain a score. According to this score, adaptive control action will be chosen. While in low-level architecture, two sub-systems are introduced, one is a differential target- driven system"},"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":"1807.05424","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-07-14T18:07:32Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"d8da09778a2feb8edc4d3907b8c1ff7312d1d2fa7c0a1ac6b563c889094c8aee","abstract_canon_sha256":"482d2c55a76209759e044227b9086597c1400ab085a018fb7482f613d0535815"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:36.519457Z","signature_b64":"6rdkue56y7WPOcDqAndu9zNx6QiEj97hjOKmjKegxt+cGs5ANzfMcYp5UfZcwGuHF8H6AE1utMOwkoPoHqqHCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"722d3fa462ed6a523aa6fbe8ca52d19245690ff918755fd5e3846fcdab256976","last_reissued_at":"2026-05-18T00:10:36.518951Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:36.518951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Reinforcement Learning Framework towards Multi-agent Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.RO","authors_text":"Huihuan Qian, Shuaijun Li, Wenhao Ding","submitted_at":"2018-07-14T18:07:32Z","abstract_excerpt":"In this paper, we propose a navigation algorithm oriented to multi-agent environment. This algorithm is expressed as a hierarchical framework that contains a Hidden Markov Model (HMM) and a Deep Reinforcement Learning (DRL) structure. For simplification, we term our method Hierarchical Navigation Reinforcement Network (HNRN). In high- level architecture, we train an HMM to evaluate the agent's perception to obtain a score. According to this score, adaptive control action will be chosen. While in low-level architecture, two sub-systems are introduced, one is a differential target- driven system"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05424","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":""},"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":"1807.05424","created_at":"2026-05-18T00:10:36.519024+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.05424v2","created_at":"2026-05-18T00:10:36.519024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05424","created_at":"2026-05-18T00:10:36.519024+00:00"},{"alias_kind":"pith_short_12","alias_value":"OIWT7JDC5VVF","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_16","alias_value":"OIWT7JDC5VVFEOVG","created_at":"2026-05-18T12:32:43.782077+00:00"},{"alias_kind":"pith_short_8","alias_value":"OIWT7JDC","created_at":"2026-05-18T12:32:43.782077+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/OIWT7JDC5VVFEOVG7PUMUUWRSJ","json":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ.json","graph_json":"https://pith.science/api/pith-number/OIWT7JDC5VVFEOVG7PUMUUWRSJ/graph.json","events_json":"https://pith.science/api/pith-number/OIWT7JDC5VVFEOVG7PUMUUWRSJ/events.json","paper":"https://pith.science/paper/OIWT7JDC"},"agent_actions":{"view_html":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ","download_json":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ.json","view_paper":"https://pith.science/paper/OIWT7JDC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.05424&json=true","fetch_graph":"https://pith.science/api/pith-number/OIWT7JDC5VVFEOVG7PUMUUWRSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/OIWT7JDC5VVFEOVG7PUMUUWRSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/action/storage_attestation","attest_author":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/action/author_attestation","sign_citation":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/action/citation_signature","submit_replication":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/action/replication_record"}},"created_at":"2026-05-18T00:10:36.519024+00:00","updated_at":"2026-05-18T00:10:36.519024+00:00"}