{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:AJSWZZJFNIDRFAJDPOCN2PRL6C","short_pith_number":"pith:AJSWZZJF","schema_version":"1.0","canonical_sha256":"02656ce5256a071281237b84dd3e2bf0a9f6bedfbddf8fab16ed2e61e3972d99","source":{"kind":"arxiv","id":"1911.05438","version":1},"attestation_state":"computed","paper":{"title":"Learning to Communicate in Multi-Agent Reinforcement Learning : A Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Etienne Bennequin, Mohamed Salah Za\\\"iem","submitted_at":"2019-11-13T13:08:46Z","abstract_excerpt":"We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a review of the recent algorithms developed to improve the agents' policy by allowing the sharing of information between agents and the learning of communication strategies, with a focus on Deep Recurrent Q-Network-based models. We also describe recent efforts to interpret the languages generated by these agents and study their properties in an attempt to generate human-language"},"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":"1911.05438","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-13T13:08:46Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"192d834b22b0557ccfbc22a9ee788f79db64da9e3308b715d201bb03a4b8d8ad","abstract_canon_sha256":"0ba7ef8d4fe121195ec7b73f4d67464990bb1326cac0df015e30f7c0e5411156"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:18:57.071357Z","signature_b64":"3D4HjTag7+bBRVcpxQBxRvQSDg5vuySJyfoBqQc+QRXvI3NYGOgU6aO1Q0afV1U1XxkJcw7hDdyKOYUY2vteBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02656ce5256a071281237b84dd3e2bf0a9f6bedfbddf8fab16ed2e61e3972d99","last_reissued_at":"2026-07-05T00:18:57.070956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:18:57.070956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Communicate in Multi-Agent Reinforcement Learning : A Review","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Etienne Bennequin, Mohamed Salah Za\\\"iem","submitted_at":"2019-11-13T13:08:46Z","abstract_excerpt":"We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a review of the recent algorithms developed to improve the agents' policy by allowing the sharing of information between agents and the learning of communication strategies, with a focus on Deep Recurrent Q-Network-based models. We also describe recent efforts to interpret the languages generated by these agents and study their properties in an attempt to generate human-language"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.05438","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/1911.05438/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":"1911.05438","created_at":"2026-07-05T00:18:57.071021+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.05438v1","created_at":"2026-07-05T00:18:57.071021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.05438","created_at":"2026-07-05T00:18:57.071021+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJSWZZJFNIDR","created_at":"2026-07-05T00:18:57.071021+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJSWZZJFNIDRFAJD","created_at":"2026-07-05T00:18:57.071021+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJSWZZJF","created_at":"2026-07-05T00:18:57.071021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.06261","citing_title":"Reducing Variance Caused by Communication in Decentralized Multi-agent Deep Reinforcement Learning","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJSWZZJFNIDRFAJDPOCN2PRL6C","json":"https://pith.science/pith/AJSWZZJFNIDRFAJDPOCN2PRL6C.json","graph_json":"https://pith.science/api/pith-number/AJSWZZJFNIDRFAJDPOCN2PRL6C/graph.json","events_json":"https://pith.science/api/pith-number/AJSWZZJFNIDRFAJDPOCN2PRL6C/events.json","paper":"https://pith.science/paper/AJSWZZJF"},"agent_actions":{"view_html":"https://pith.science/pith/AJSWZZJFNIDRFAJDPOCN2PRL6C","download_json":"https://pith.science/pith/AJSWZZJFNIDRFAJDPOCN2PRL6C.json","view_paper":"https://pith.science/paper/AJSWZZJF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.05438&json=true","fetch_graph":"https://pith.science/api/pith-number/AJSWZZJFNIDRFAJDPOCN2PRL6C/graph.json","fetch_events":"https://pith.science/api/pith-number/AJSWZZJFNIDRFAJDPOCN2PRL6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJSWZZJFNIDRFAJDPOCN2PRL6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJSWZZJFNIDRFAJDPOCN2PRL6C/action/storage_attestation","attest_author":"https://pith.science/pith/AJSWZZJFNIDRFAJDPOCN2PRL6C/action/author_attestation","sign_citation":"https://pith.science/pith/AJSWZZJFNIDRFAJDPOCN2PRL6C/action/citation_signature","submit_replication":"https://pith.science/pith/AJSWZZJFNIDRFAJDPOCN2PRL6C/action/replication_record"}},"created_at":"2026-07-05T00:18:57.071021+00:00","updated_at":"2026-07-05T00:18:57.071021+00:00"}