{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:ON7GJLRWZAXEZ7EG56XOFUM7V4","short_pith_number":"pith:ON7GJLRW","schema_version":"1.0","canonical_sha256":"737e64ae36c82e4cfc86efaee2d19faf2b2e8fa15c7d618a0a9975cbad33a744","source":{"kind":"arxiv","id":"1602.02672","version":1},"attestation_state":"computed","paper":{"title":"Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jakob N. Foerster, Nando de Freitas, Shimon Whiteson, Yannis M. Assael","submitted_at":"2016-02-08T18:01:35Z","abstract_excerpt":"We propose deep distributed recurrent Q-networks (DDRQN), which enable teams of agents to learn to solve communication-based coordination tasks. In these tasks, the agents are not given any pre-designed communication protocol. Therefore, in order to successfully communicate, they must first automatically develop and agree upon their own communication protocol. We present empirical results on two multi-agent learning problems based on well-known riddles, demonstrating that DDRQN can successfully solve such tasks and discover elegant communication protocols to do so. To our knowledge, this is th"},"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":"1602.02672","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2016-02-08T18:01:35Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"afda5086ea34d7330e4c59fcf746a16958f33e6e44046f1c0100719bf2389ce0","abstract_canon_sha256":"3e3eac5b38261035f76ff69bac0e70071def541d344a57234c79ad8b680abcb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:09.193603Z","signature_b64":"MvUcNnPLoTAtvfijNzP/CSApG0Kr1eq4wipiHMhnZRSHrK5OMD6QdbPfnt2jCaqYUMHUdRsV0bvYtTpB9x0TAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"737e64ae36c82e4cfc86efaee2d19faf2b2e8fa15c7d618a0a9975cbad33a744","last_reissued_at":"2026-05-18T01:21:09.192900Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:09.192900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Communicate to Solve Riddles with Deep Distributed Recurrent Q-Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jakob N. Foerster, Nando de Freitas, Shimon Whiteson, Yannis M. Assael","submitted_at":"2016-02-08T18:01:35Z","abstract_excerpt":"We propose deep distributed recurrent Q-networks (DDRQN), which enable teams of agents to learn to solve communication-based coordination tasks. In these tasks, the agents are not given any pre-designed communication protocol. Therefore, in order to successfully communicate, they must first automatically develop and agree upon their own communication protocol. We present empirical results on two multi-agent learning problems based on well-known riddles, demonstrating that DDRQN can successfully solve such tasks and discover elegant communication protocols to do so. To our knowledge, this is th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.02672","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":""},"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":"1602.02672","created_at":"2026-05-18T01:21:09.193000+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.02672v1","created_at":"2026-05-18T01:21:09.193000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.02672","created_at":"2026-05-18T01:21:09.193000+00:00"},{"alias_kind":"pith_short_12","alias_value":"ON7GJLRWZAXE","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_16","alias_value":"ON7GJLRWZAXEZ7EG","created_at":"2026-05-18T12:30:36.002864+00:00"},{"alias_kind":"pith_short_8","alias_value":"ON7GJLRW","created_at":"2026-05-18T12:30:36.002864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ON7GJLRWZAXEZ7EG56XOFUM7V4","json":"https://pith.science/pith/ON7GJLRWZAXEZ7EG56XOFUM7V4.json","graph_json":"https://pith.science/api/pith-number/ON7GJLRWZAXEZ7EG56XOFUM7V4/graph.json","events_json":"https://pith.science/api/pith-number/ON7GJLRWZAXEZ7EG56XOFUM7V4/events.json","paper":"https://pith.science/paper/1602.02672"},"agent_actions":{"view_html":"https://pith.science/pith/ON7GJLRWZAXEZ7EG56XOFUM7V4","download_json":"https://pith.science/pith/ON7GJLRWZAXEZ7EG56XOFUM7V4.json","view_paper":"https://pith.science/paper/1602.02672","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.02672&json=true","fetch_graph":"https://pith.science/api/pith-number/ON7GJLRWZAXEZ7EG56XOFUM7V4/graph.json","fetch_events":"https://pith.science/api/pith-number/ON7GJLRWZAXEZ7EG56XOFUM7V4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ON7GJLRWZAXEZ7EG56XOFUM7V4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ON7GJLRWZAXEZ7EG56XOFUM7V4/action/storage_attestation","attest_author":"https://pith.science/pith/ON7GJLRWZAXEZ7EG56XOFUM7V4/action/author_attestation","sign_citation":"https://pith.science/pith/ON7GJLRWZAXEZ7EG56XOFUM7V4/action/citation_signature","submit_replication":"https://pith.science/pith/ON7GJLRWZAXEZ7EG56XOFUM7V4/action/replication_record"}},"created_at":"2026-05-18T01:21:09.193000+00:00","updated_at":"2026-05-18T01:21:09.193000+00:00"}