{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5OED3VLOFDLIZYJU5SWILH3NX6","short_pith_number":"pith:5OED3VLO","schema_version":"1.0","canonical_sha256":"eb883dd56e28d68ce134ecac859f6dbf8be9f91889101b41623c19af441d834a","source":{"kind":"arxiv","id":"1902.06740","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Communication Topologies Between Learning Agents in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhimanyu Dubey, Alex Pentland, Anirudh Goyal, Dan Calacci, Dhaval Adjodah, Esteban Moro, Peter Krafft","submitted_at":"2019-02-16T19:54:52Z","abstract_excerpt":"A common technique to improve learning performance in deep reinforcement learning (DRL) and many other machine learning algorithms is to run multiple learning agents in parallel. A neglected component in the development of these algorithms has been how best to arrange the learning agents involved to improve distributed search. Here we draw upon results from the networked optimization literatures suggesting that arranging learning agents in communication networks other than fully connected topologies (the implicit way agents are commonly arranged in) can improve learning. We explore the relativ"},"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":"1902.06740","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-02-16T19:54:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3c1d591d76eebc202a3aea51a0d519ed53629be64e383fef551e2425a198e984","abstract_canon_sha256":"fdacbbb7c7a126b247507b699f681c3d632403fee68604867b2fea7131e4ec88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:47:37.170713Z","signature_b64":"8fa5eaCKlgiaIzjjmovnIKiFifRLckNvPwh0x+6A2TEfZVb46TR9Fnyt82woV7EI+uDVw4+LjKqnPDE2kF37Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb883dd56e28d68ce134ecac859f6dbf8be9f91889101b41623c19af441d834a","last_reissued_at":"2026-07-05T00:47:37.170216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:47:37.170216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Communication Topologies Between Learning Agents in Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhimanyu Dubey, Alex Pentland, Anirudh Goyal, Dan Calacci, Dhaval Adjodah, Esteban Moro, Peter Krafft","submitted_at":"2019-02-16T19:54:52Z","abstract_excerpt":"A common technique to improve learning performance in deep reinforcement learning (DRL) and many other machine learning algorithms is to run multiple learning agents in parallel. A neglected component in the development of these algorithms has been how best to arrange the learning agents involved to improve distributed search. Here we draw upon results from the networked optimization literatures suggesting that arranging learning agents in communication networks other than fully connected topologies (the implicit way agents are commonly arranged in) can improve learning. We explore the relativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06740","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/1902.06740/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":"1902.06740","created_at":"2026-07-05T00:47:37.170273+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.06740v2","created_at":"2026-07-05T00:47:37.170273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06740","created_at":"2026-07-05T00:47:37.170273+00:00"},{"alias_kind":"pith_short_12","alias_value":"5OED3VLOFDLI","created_at":"2026-07-05T00:47:37.170273+00:00"},{"alias_kind":"pith_short_16","alias_value":"5OED3VLOFDLIZYJU","created_at":"2026-07-05T00:47:37.170273+00:00"},{"alias_kind":"pith_short_8","alias_value":"5OED3VLO","created_at":"2026-07-05T00:47:37.170273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20962","citing_title":"Heterogeneous Policy Networks for Composite Robot Team Communication and Coordination","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5OED3VLOFDLIZYJU5SWILH3NX6","json":"https://pith.science/pith/5OED3VLOFDLIZYJU5SWILH3NX6.json","graph_json":"https://pith.science/api/pith-number/5OED3VLOFDLIZYJU5SWILH3NX6/graph.json","events_json":"https://pith.science/api/pith-number/5OED3VLOFDLIZYJU5SWILH3NX6/events.json","paper":"https://pith.science/paper/5OED3VLO"},"agent_actions":{"view_html":"https://pith.science/pith/5OED3VLOFDLIZYJU5SWILH3NX6","download_json":"https://pith.science/pith/5OED3VLOFDLIZYJU5SWILH3NX6.json","view_paper":"https://pith.science/paper/5OED3VLO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.06740&json=true","fetch_graph":"https://pith.science/api/pith-number/5OED3VLOFDLIZYJU5SWILH3NX6/graph.json","fetch_events":"https://pith.science/api/pith-number/5OED3VLOFDLIZYJU5SWILH3NX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5OED3VLOFDLIZYJU5SWILH3NX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5OED3VLOFDLIZYJU5SWILH3NX6/action/storage_attestation","attest_author":"https://pith.science/pith/5OED3VLOFDLIZYJU5SWILH3NX6/action/author_attestation","sign_citation":"https://pith.science/pith/5OED3VLOFDLIZYJU5SWILH3NX6/action/citation_signature","submit_replication":"https://pith.science/pith/5OED3VLOFDLIZYJU5SWILH3NX6/action/replication_record"}},"created_at":"2026-07-05T00:47:37.170273+00:00","updated_at":"2026-07-05T00:47:37.170273+00:00"}