{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:OIWT7JDC5VVFEOVG7PUMUUWRSJ","short_pith_number":"pith:OIWT7JDC","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"},"canonical_sha256":"722d3fa462ed6a523aa6fbe8ca52d19245690ff918755fd5e3846fcdab256976","source":{"kind":"arxiv","id":"1807.05424","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05424","created_at":"2026-05-18T00:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05424v2","created_at":"2026-05-18T00:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05424","created_at":"2026-05-18T00:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"OIWT7JDC5VVF","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OIWT7JDC5VVFEOVG","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OIWT7JDC","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:OIWT7JDC5VVFEOVG7PUMUUWRSJ","target":"record","payload":{"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"},"canonical_sha256":"722d3fa462ed6a523aa6fbe8ca52d19245690ff918755fd5e3846fcdab256976","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"},"source_kind":"arxiv","source_id":"1807.05424","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wddf2iz7RiAabnaorqket9B5wCla5FPKVu8K2Lc3EYkktZResFoZ2EGRKet1ZbWd822I9RCpBqcUHGQAPTjwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T17:52:13.119269Z"},"content_sha256":"6a06d0a83ae4e0b48fe5043f4054c93a6dc48f41414129664c866a1ac9dcd2d3","schema_version":"1.0","event_id":"sha256:6a06d0a83ae4e0b48fe5043f4054c93a6dc48f41414129664c866a1ac9dcd2d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:OIWT7JDC5VVFEOVG7PUMUUWRSJ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:10:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"beg5GFmnR0WCq53lM117TS/95nlmB/DQ0eIHQV1qyBVZHMFyTbjJm3tONKBYIH0LoFAeMDNG21u5Z34BvKEHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T17:52:13.119963Z"},"content_sha256":"92a05ac7c4547035ce3bf4bf5f194fe1f39feb13099c61a207a1f04ae2a9e6db","schema_version":"1.0","event_id":"sha256:92a05ac7c4547035ce3bf4bf5f194fe1f39feb13099c61a207a1f04ae2a9e6db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/bundle.json","state_url":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T17:52:13Z","links":{"resolver":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ","bundle":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/bundle.json","state":"https://pith.science/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OIWT7JDC5VVFEOVG7PUMUUWRSJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:OIWT7JDC5VVFEOVG7PUMUUWRSJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"482d2c55a76209759e044227b9086597c1400ab085a018fb7482f613d0535815","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-07-14T18:07:32Z","title_canon_sha256":"d8da09778a2feb8edc4d3907b8c1ff7312d1d2fa7c0a1ac6b563c889094c8aee"},"schema_version":"1.0","source":{"id":"1807.05424","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.05424","created_at":"2026-05-18T00:10:36Z"},{"alias_kind":"arxiv_version","alias_value":"1807.05424v2","created_at":"2026-05-18T00:10:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.05424","created_at":"2026-05-18T00:10:36Z"},{"alias_kind":"pith_short_12","alias_value":"OIWT7JDC5VVF","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"OIWT7JDC5VVFEOVG","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"OIWT7JDC","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:92a05ac7c4547035ce3bf4bf5f194fe1f39feb13099c61a207a1f04ae2a9e6db","target":"graph","created_at":"2026-05-18T00:10:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Huihuan Qian, Shuaijun Li, Wenhao Ding","cross_cats":["cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-07-14T18:07:32Z","title":"Hierarchical Reinforcement Learning Framework towards Multi-agent Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.05424","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6a06d0a83ae4e0b48fe5043f4054c93a6dc48f41414129664c866a1ac9dcd2d3","target":"record","created_at":"2026-05-18T00:10:36Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"482d2c55a76209759e044227b9086597c1400ab085a018fb7482f613d0535815","cross_cats_sorted":["cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2018-07-14T18:07:32Z","title_canon_sha256":"d8da09778a2feb8edc4d3907b8c1ff7312d1d2fa7c0a1ac6b563c889094c8aee"},"schema_version":"1.0","source":{"id":"1807.05424","kind":"arxiv","version":2}},"canonical_sha256":"722d3fa462ed6a523aa6fbe8ca52d19245690ff918755fd5e3846fcdab256976","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"722d3fa462ed6a523aa6fbe8ca52d19245690ff918755fd5e3846fcdab256976","first_computed_at":"2026-05-18T00:10:36.518951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:10:36.518951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6rdkue56y7WPOcDqAndu9zNx6QiEj97hjOKmjKegxt+cGs5ANzfMcYp5UfZcwGuHF8H6AE1utMOwkoPoHqqHCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:10:36.519457Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.05424","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a06d0a83ae4e0b48fe5043f4054c93a6dc48f41414129664c866a1ac9dcd2d3","sha256:92a05ac7c4547035ce3bf4bf5f194fe1f39feb13099c61a207a1f04ae2a9e6db"],"state_sha256":"1b7b2b1cd87bd71a9e2c2f82359196664bf4231ed2a165ec85b85643e7adb061"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kdTKRHlUR81W4gDiwDbJngaqbdKhWX4l99DBbzZ+4rguFUSIyPPdTROhQOaQrtDs8X2FPaSw/Qmoclk9zH3kCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T17:52:13.124047Z","bundle_sha256":"66688f9dffd131198646844fb65a750653a256422b2e103405caef14b1f036d3"}}