{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BVVQNH437NJGDBIHPZNPCKZBAP","short_pith_number":"pith:BVVQNH43","schema_version":"1.0","canonical_sha256":"0d6b069f9bfb526185077e5af12b2103faabe8ba8189c259b33723cb1fb7d60e","source":{"kind":"arxiv","id":"2407.08164","version":2},"attestation_state":"computed","paper":{"title":"Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.RO"],"primary_cat":"cs.AI","authors_text":"Junkang Liang, Kui Zhang, Pu Feng, Rongye Shi, Size Wang, Wenjun Wu, Xin Ji, Xin Yu, Yiting Chen","submitted_at":"2024-07-11T03:55:55Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in execution, lacking global signals. Inspired by human societal consensus mechanisms, we introduce the Hierarchical Consensus-based Multi-Agent Reinforcement Learning (HC-MARL) framework to address this limitation. HC-MARL employs contrastive learning to foster a global consensus among agents, enabling cooperative behavior without direct communication. This approach en"},"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":"2407.08164","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-07-11T03:55:55Z","cross_cats_sorted":["cs.MA","cs.RO"],"title_canon_sha256":"aaa82f9b2d262069c74eb7531723c77cfdb4d7c9a92096e36f86e9f0f42e3a1b","abstract_canon_sha256":"1968f4ab38b3dc767ed1a17f30b576f25e6911793f8ec596fde67ebe3fdc0ab8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:25.164074Z","signature_b64":"fr4W9PjWRqVsAeTEmYPpcU3UeUTjVpQf/VzNsJlmlLBswCwLsKK/MgrUhaR79n5GcIwBVWxiFZNs0oTe+4jMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d6b069f9bfb526185077e5af12b2103faabe8ba8189c259b33723cb1fb7d60e","last_reissued_at":"2026-07-05T08:58:25.163586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:25.163586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Consensus-Based Multi-Agent Reinforcement Learning for Multi-Robot Cooperation Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","cs.RO"],"primary_cat":"cs.AI","authors_text":"Junkang Liang, Kui Zhang, Pu Feng, Rongye Shi, Size Wang, Wenjun Wu, Xin Ji, Xin Yu, Yiting Chen","submitted_at":"2024-07-11T03:55:55Z","abstract_excerpt":"In multi-agent reinforcement learning (MARL), the Centralized Training with Decentralized Execution (CTDE) framework is pivotal but struggles due to a gap: global state guidance in training versus reliance on local observations in execution, lacking global signals. Inspired by human societal consensus mechanisms, we introduce the Hierarchical Consensus-based Multi-Agent Reinforcement Learning (HC-MARL) framework to address this limitation. HC-MARL employs contrastive learning to foster a global consensus among agents, enabling cooperative behavior without direct communication. This approach en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08164","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/2407.08164/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":"2407.08164","created_at":"2026-07-05T08:58:25.163648+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08164v2","created_at":"2026-07-05T08:58:25.163648+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08164","created_at":"2026-07-05T08:58:25.163648+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVVQNH437NJG","created_at":"2026-07-05T08:58:25.163648+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVVQNH437NJGDBIH","created_at":"2026-07-05T08:58:25.163648+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVVQNH43","created_at":"2026-07-05T08:58:25.163648+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.12683","citing_title":"A Taxonomy of Hierarchical Multi-Agent Systems: Design Patterns, Coordination Mechanisms, and Industrial Applications","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BVVQNH437NJGDBIHPZNPCKZBAP","json":"https://pith.science/pith/BVVQNH437NJGDBIHPZNPCKZBAP.json","graph_json":"https://pith.science/api/pith-number/BVVQNH437NJGDBIHPZNPCKZBAP/graph.json","events_json":"https://pith.science/api/pith-number/BVVQNH437NJGDBIHPZNPCKZBAP/events.json","paper":"https://pith.science/paper/BVVQNH43"},"agent_actions":{"view_html":"https://pith.science/pith/BVVQNH437NJGDBIHPZNPCKZBAP","download_json":"https://pith.science/pith/BVVQNH437NJGDBIHPZNPCKZBAP.json","view_paper":"https://pith.science/paper/BVVQNH43","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08164&json=true","fetch_graph":"https://pith.science/api/pith-number/BVVQNH437NJGDBIHPZNPCKZBAP/graph.json","fetch_events":"https://pith.science/api/pith-number/BVVQNH437NJGDBIHPZNPCKZBAP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVVQNH437NJGDBIHPZNPCKZBAP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVVQNH437NJGDBIHPZNPCKZBAP/action/storage_attestation","attest_author":"https://pith.science/pith/BVVQNH437NJGDBIHPZNPCKZBAP/action/author_attestation","sign_citation":"https://pith.science/pith/BVVQNH437NJGDBIHPZNPCKZBAP/action/citation_signature","submit_replication":"https://pith.science/pith/BVVQNH437NJGDBIHPZNPCKZBAP/action/replication_record"}},"created_at":"2026-07-05T08:58:25.163648+00:00","updated_at":"2026-07-05T08:58:25.163648+00:00"}