{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:TBLOPPEF6O75FCLDNRHA5ZP4GL","short_pith_number":"pith:TBLOPPEF","schema_version":"1.0","canonical_sha256":"9856e7bc85f3bfd289636c4e0ee5fc32c10b5f0a5332ffb7c34ed3f0a0cbc229","source":{"kind":"arxiv","id":"2203.08975","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Changxi Zhu, Mehdi Dastani, Shihan Wang","submitted_at":"2022-03-16T22:39:46Z","abstract_excerpt":"Communication is an effective mechanism for coordinating the behaviors of multiple agents, broadening their views of the environment, and to support their collaborations. In the field of multi-agent deep reinforcement learning (MADRL), agents can improve the overall learning performance and achieve their objectives by communication. Agents can communicate various types of messages, either to all agents or to specific agent groups, or conditioned on specific constraints. With the growing body of research work in MADRL with communication (Comm-MADRL), there is a lack of a systematic and structur"},"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":"2203.08975","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2022-03-16T22:39:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"640404d4955ef5342a8e578018ac06c9d98fbf11e59cd81750f851ea7871bdb3","abstract_canon_sha256":"ecd3d6f1761e336ac07be75e2205d58d1b8c305b3454b97d1c7445de95c770e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:12.003370Z","signature_b64":"743wgcaMWid19OnK+HeoQ4Ha7em0lmtTKPTGIvK+T7qeOlHBWoLPYCh8nl8m6X+bGWXbaUonx06ZZYaKiRlmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9856e7bc85f3bfd289636c4e0ee5fc32c10b5f0a5332ffb7c34ed3f0a0cbc229","last_reissued_at":"2026-07-05T09:22:12.002923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:12.002923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Multi-Agent Deep Reinforcement Learning with Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Changxi Zhu, Mehdi Dastani, Shihan Wang","submitted_at":"2022-03-16T22:39:46Z","abstract_excerpt":"Communication is an effective mechanism for coordinating the behaviors of multiple agents, broadening their views of the environment, and to support their collaborations. In the field of multi-agent deep reinforcement learning (MADRL), agents can improve the overall learning performance and achieve their objectives by communication. Agents can communicate various types of messages, either to all agents or to specific agent groups, or conditioned on specific constraints. With the growing body of research work in MADRL with communication (Comm-MADRL), there is a lack of a systematic and structur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.08975","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/2203.08975/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":"2203.08975","created_at":"2026-07-05T09:22:12.002980+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.08975v2","created_at":"2026-07-05T09:22:12.002980+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.08975","created_at":"2026-07-05T09:22:12.002980+00:00"},{"alias_kind":"pith_short_12","alias_value":"TBLOPPEF6O75","created_at":"2026-07-05T09:22:12.002980+00:00"},{"alias_kind":"pith_short_16","alias_value":"TBLOPPEF6O75FCLD","created_at":"2026-07-05T09:22:12.002980+00:00"},{"alias_kind":"pith_short_8","alias_value":"TBLOPPEF","created_at":"2026-07-05T09:22:12.002980+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20701","citing_title":"BARD-MARL: Byzantine-Agent Detection for Learned Communication in Multi-Agent Reinforcement Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08064","citing_title":"Cooperative Long Rope Skipping via Multi-Agent Reinforcement Learning","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28764","citing_title":"SwarmHarness: Skill-Based Task Routing via Decentralized Incentive-Aligned AI Agent Networks","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00558","citing_title":"Asynchronous Cooperative Multi-Agent Reinforcement Learning with Limited Communication","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09028","citing_title":"Plasticity-Enhanced Multi-Agent Mixture of Experts for Dynamic Objective Adaptation in UAVs-Assisted Emergency Communication Networks","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TBLOPPEF6O75FCLDNRHA5ZP4GL","json":"https://pith.science/pith/TBLOPPEF6O75FCLDNRHA5ZP4GL.json","graph_json":"https://pith.science/api/pith-number/TBLOPPEF6O75FCLDNRHA5ZP4GL/graph.json","events_json":"https://pith.science/api/pith-number/TBLOPPEF6O75FCLDNRHA5ZP4GL/events.json","paper":"https://pith.science/paper/TBLOPPEF"},"agent_actions":{"view_html":"https://pith.science/pith/TBLOPPEF6O75FCLDNRHA5ZP4GL","download_json":"https://pith.science/pith/TBLOPPEF6O75FCLDNRHA5ZP4GL.json","view_paper":"https://pith.science/paper/TBLOPPEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.08975&json=true","fetch_graph":"https://pith.science/api/pith-number/TBLOPPEF6O75FCLDNRHA5ZP4GL/graph.json","fetch_events":"https://pith.science/api/pith-number/TBLOPPEF6O75FCLDNRHA5ZP4GL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TBLOPPEF6O75FCLDNRHA5ZP4GL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TBLOPPEF6O75FCLDNRHA5ZP4GL/action/storage_attestation","attest_author":"https://pith.science/pith/TBLOPPEF6O75FCLDNRHA5ZP4GL/action/author_attestation","sign_citation":"https://pith.science/pith/TBLOPPEF6O75FCLDNRHA5ZP4GL/action/citation_signature","submit_replication":"https://pith.science/pith/TBLOPPEF6O75FCLDNRHA5ZP4GL/action/replication_record"}},"created_at":"2026-07-05T09:22:12.002980+00:00","updated_at":"2026-07-05T09:22:12.002980+00:00"}