{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:5SBLJY24MDIWCW3RZGSDNGBPAV","short_pith_number":"pith:5SBLJY24","schema_version":"1.0","canonical_sha256":"ec82b4e35c60d1615b71c9a436982f0550b431655c840846654dbc77772d2fe5","source":{"kind":"arxiv","id":"1810.11187","version":2},"attestation_state":"computed","paper":{"title":"TarMAC: Targeted Multi-Agent Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Das, Devi Parikh, Dhruv Batra, Joelle Pineau, Joshua Romoff, Michael Rabbat, Th\\'eophile Gervet","submitted_at":"2018-10-26T04:22:58Z","abstract_excerpt":"We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This targeting behavior is learnt solely from downstream task-specific reward without any communication supervision. We additionally augment this with a multi-round communication approach where agents coordinate via multiple rounds of communication before taking actions in the environment. We evaluate our approach on a diverse set of cooperative multi-agent task"},"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":"1810.11187","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-26T04:22:58Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"0f15ae084ddd3b644fb760badaf6d1394b83c84470d95b33451c2f814384dcd4","abstract_canon_sha256":"bf18f9a809f0ea9f65be34b970416cad844d8e4ed64ea932519d9907a2db4414"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:59.083366Z","signature_b64":"F+Z6PBg2NlE+tnHUh9FlU9457s/sIUNOyDo+RRtUMGU3Dm40feN+FNDeevmtWaBCs4j7cO1ngDLsyn98vRLKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec82b4e35c60d1615b71c9a436982f0550b431655c840846654dbc77772d2fe5","last_reissued_at":"2026-07-05T00:42:59.082960Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:59.082960Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TarMAC: Targeted Multi-Agent Communication","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Das, Devi Parikh, Dhruv Batra, Joelle Pineau, Joshua Romoff, Michael Rabbat, Th\\'eophile Gervet","submitted_at":"2018-10-26T04:22:58Z","abstract_excerpt":"We propose a targeted communication architecture for multi-agent reinforcement learning, where agents learn both what messages to send and whom to address them to while performing cooperative tasks in partially-observable environments. This targeting behavior is learnt solely from downstream task-specific reward without any communication supervision. We additionally augment this with a multi-round communication approach where agents coordinate via multiple rounds of communication before taking actions in the environment. We evaluate our approach on a diverse set of cooperative multi-agent task"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11187","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/1810.11187/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":"1810.11187","created_at":"2026-07-05T00:42:59.083016+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.11187v2","created_at":"2026-07-05T00:42:59.083016+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11187","created_at":"2026-07-05T00:42:59.083016+00:00"},{"alias_kind":"pith_short_12","alias_value":"5SBLJY24MDIW","created_at":"2026-07-05T00:42:59.083016+00:00"},{"alias_kind":"pith_short_16","alias_value":"5SBLJY24MDIWCW3R","created_at":"2026-07-05T00:42:59.083016+00:00"},{"alias_kind":"pith_short_8","alias_value":"5SBLJY24","created_at":"2026-07-05T00:42:59.083016+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11249","citing_title":"MASK: Multi-Agent Semantic K-Scheduling for Risk-Sensitive 6G Robotics","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2502.00558","citing_title":"Asynchronous Cooperative Multi-Agent Reinforcement Learning with Limited Communication","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5SBLJY24MDIWCW3RZGSDNGBPAV","json":"https://pith.science/pith/5SBLJY24MDIWCW3RZGSDNGBPAV.json","graph_json":"https://pith.science/api/pith-number/5SBLJY24MDIWCW3RZGSDNGBPAV/graph.json","events_json":"https://pith.science/api/pith-number/5SBLJY24MDIWCW3RZGSDNGBPAV/events.json","paper":"https://pith.science/paper/5SBLJY24"},"agent_actions":{"view_html":"https://pith.science/pith/5SBLJY24MDIWCW3RZGSDNGBPAV","download_json":"https://pith.science/pith/5SBLJY24MDIWCW3RZGSDNGBPAV.json","view_paper":"https://pith.science/paper/5SBLJY24","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.11187&json=true","fetch_graph":"https://pith.science/api/pith-number/5SBLJY24MDIWCW3RZGSDNGBPAV/graph.json","fetch_events":"https://pith.science/api/pith-number/5SBLJY24MDIWCW3RZGSDNGBPAV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5SBLJY24MDIWCW3RZGSDNGBPAV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5SBLJY24MDIWCW3RZGSDNGBPAV/action/storage_attestation","attest_author":"https://pith.science/pith/5SBLJY24MDIWCW3RZGSDNGBPAV/action/author_attestation","sign_citation":"https://pith.science/pith/5SBLJY24MDIWCW3RZGSDNGBPAV/action/citation_signature","submit_replication":"https://pith.science/pith/5SBLJY24MDIWCW3RZGSDNGBPAV/action/replication_record"}},"created_at":"2026-07-05T00:42:59.083016+00:00","updated_at":"2026-07-05T00:42:59.083016+00:00"}