{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NVF3E56TS54PWHHB6BMNYH6HZW","short_pith_number":"pith:NVF3E56T","schema_version":"1.0","canonical_sha256":"6d4bb277d39778fb1ce1f058dc1fc7cdb77f26cb34b2b8d35ab4725c9bdd63e2","source":{"kind":"arxiv","id":"2208.01769","version":1},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning for Multi-Agent Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Arrasy Rahman, Balint Gyevnar, Cheng Wang, Cillian Brewitt, Elliot Fosong, Filippos Christianos, Georgios Papoudakis, Giuseppe Vecchio, Ibrahim H. Ahmed, Ignacio Carlucho, Lukas Sch\\\"afer, Massimiliano Tamborski, Mhairi Dunion, Samuel Garcin, Shangmin Guo, Stefano V. Albrecht, Trevor McInroe","submitted_at":"2022-08-02T21:55:56Z","abstract_excerpt":"The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systems control, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observatio"},"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":"2208.01769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2022-08-02T21:55:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"e01a1c10cad9daef447ee7d6b72571c8ada5d45eddb615602778a77136820b59","abstract_canon_sha256":"256951b8e847180375f6c7d71fe0d8ae72a70d0924676a99fec32b665435f952"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:45:40.083604Z","signature_b64":"oCtde0F2IG2f0K7RI0nH3IrOwOAMU+CV4aX95XWZcaQ8mLukd81cMBo/arhXwHaxdghDYCAmqJycscw+3VAYBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d4bb277d39778fb1ce1f058dc1fc7cdb77f26cb34b2b8d35ab4725c9bdd63e2","last_reissued_at":"2026-07-05T04:45:40.083156Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:45:40.083156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning for Multi-Agent Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Arrasy Rahman, Balint Gyevnar, Cheng Wang, Cillian Brewitt, Elliot Fosong, Filippos Christianos, Georgios Papoudakis, Giuseppe Vecchio, Ibrahim H. Ahmed, Ignacio Carlucho, Lukas Sch\\\"afer, Massimiliano Tamborski, Mhairi Dunion, Samuel Garcin, Shangmin Guo, Stefano V. Albrecht, Trevor McInroe","submitted_at":"2022-08-02T21:55:56Z","abstract_excerpt":"The development of autonomous agents which can interact with other agents to accomplish a given task is a core area of research in artificial intelligence and machine learning. Towards this goal, the Autonomous Agents Research Group develops novel machine learning algorithms for autonomous systems control, with a specific focus on deep reinforcement learning and multi-agent reinforcement learning. Research problems include scalable learning of coordinated agent policies and inter-agent communication; reasoning about the behaviours, goals, and composition of other agents from limited observatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.01769","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/2208.01769/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":"2208.01769","created_at":"2026-07-05T04:45:40.083212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.01769v1","created_at":"2026-07-05T04:45:40.083212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.01769","created_at":"2026-07-05T04:45:40.083212+00:00"},{"alias_kind":"pith_short_12","alias_value":"NVF3E56TS54P","created_at":"2026-07-05T04:45:40.083212+00:00"},{"alias_kind":"pith_short_16","alias_value":"NVF3E56TS54PWHHB","created_at":"2026-07-05T04:45:40.083212+00:00"},{"alias_kind":"pith_short_8","alias_value":"NVF3E56T","created_at":"2026-07-05T04:45:40.083212+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/NVF3E56TS54PWHHB6BMNYH6HZW","json":"https://pith.science/pith/NVF3E56TS54PWHHB6BMNYH6HZW.json","graph_json":"https://pith.science/api/pith-number/NVF3E56TS54PWHHB6BMNYH6HZW/graph.json","events_json":"https://pith.science/api/pith-number/NVF3E56TS54PWHHB6BMNYH6HZW/events.json","paper":"https://pith.science/paper/NVF3E56T"},"agent_actions":{"view_html":"https://pith.science/pith/NVF3E56TS54PWHHB6BMNYH6HZW","download_json":"https://pith.science/pith/NVF3E56TS54PWHHB6BMNYH6HZW.json","view_paper":"https://pith.science/paper/NVF3E56T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.01769&json=true","fetch_graph":"https://pith.science/api/pith-number/NVF3E56TS54PWHHB6BMNYH6HZW/graph.json","fetch_events":"https://pith.science/api/pith-number/NVF3E56TS54PWHHB6BMNYH6HZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NVF3E56TS54PWHHB6BMNYH6HZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NVF3E56TS54PWHHB6BMNYH6HZW/action/storage_attestation","attest_author":"https://pith.science/pith/NVF3E56TS54PWHHB6BMNYH6HZW/action/author_attestation","sign_citation":"https://pith.science/pith/NVF3E56TS54PWHHB6BMNYH6HZW/action/citation_signature","submit_replication":"https://pith.science/pith/NVF3E56TS54PWHHB6BMNYH6HZW/action/replication_record"}},"created_at":"2026-07-05T04:45:40.083212+00:00","updated_at":"2026-07-05T04:45:40.083212+00:00"}