{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:Z6SZVBWY3WF3SFPCI4RXRYMOOY","short_pith_number":"pith:Z6SZVBWY","schema_version":"1.0","canonical_sha256":"cfa59a86d8dd8bb915e2472378e18e76144844077a8144c565ecde6290a1822a","source":{"kind":"arxiv","id":"1805.08948","version":2},"attestation_state":"computed","paper":{"title":"Scalable Coordinated Exploration in Concurrent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Roy, Ian Osband, Maria Dimakopoulou","submitted_at":"2018-05-23T03:36:01Z","abstract_excerpt":"We consider a team of reinforcement learning agents that concurrently operate in a common environment, and we develop an approach to efficient coordinated exploration that is suitable for problems of practical scale. Our approach builds on seed sampling (Dimakopoulou and Van Roy, 2018) and randomized value function learning (Osband et al., 2016). We demonstrate that, for simple tabular contexts, the approach is competitive with previously proposed tabular model learning methods (Dimakopoulou and Van Roy, 2018). With a higher-dimensional problem and a neural network value function representatio"},"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":"1805.08948","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-23T03:36:01Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"e15cf273d38d7b97eabe840c2a444139fe818de475da6b5353e4ddf39d806388","abstract_canon_sha256":"e94475dea29327f21199954df791f86cb5a237353eff2e60a601e4c855437c88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:14.261808Z","signature_b64":"AjmK1CP5chRj5o53kmYIUkyHaC4H9jElEHUN4qi1EeswN6EJyCZspi5335gM0ArR8/I/oq2D82wY1lZtyEzoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfa59a86d8dd8bb915e2472378e18e76144844077a8144c565ecde6290a1822a","last_reissued_at":"2026-05-17T23:58:14.261327Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:14.261327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalable Coordinated Exploration in Concurrent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Van Roy, Ian Osband, Maria Dimakopoulou","submitted_at":"2018-05-23T03:36:01Z","abstract_excerpt":"We consider a team of reinforcement learning agents that concurrently operate in a common environment, and we develop an approach to efficient coordinated exploration that is suitable for problems of practical scale. Our approach builds on seed sampling (Dimakopoulou and Van Roy, 2018) and randomized value function learning (Osband et al., 2016). We demonstrate that, for simple tabular contexts, the approach is competitive with previously proposed tabular model learning methods (Dimakopoulou and Van Roy, 2018). With a higher-dimensional problem and a neural network value function representatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08948","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":""},"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":"1805.08948","created_at":"2026-05-17T23:58:14.261394+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.08948v2","created_at":"2026-05-17T23:58:14.261394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08948","created_at":"2026-05-17T23:58:14.261394+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z6SZVBWY3WF3","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z6SZVBWY3WF3SFPC","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z6SZVBWY","created_at":"2026-05-18T12:33:04.347982+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/Z6SZVBWY3WF3SFPCI4RXRYMOOY","json":"https://pith.science/pith/Z6SZVBWY3WF3SFPCI4RXRYMOOY.json","graph_json":"https://pith.science/api/pith-number/Z6SZVBWY3WF3SFPCI4RXRYMOOY/graph.json","events_json":"https://pith.science/api/pith-number/Z6SZVBWY3WF3SFPCI4RXRYMOOY/events.json","paper":"https://pith.science/paper/Z6SZVBWY"},"agent_actions":{"view_html":"https://pith.science/pith/Z6SZVBWY3WF3SFPCI4RXRYMOOY","download_json":"https://pith.science/pith/Z6SZVBWY3WF3SFPCI4RXRYMOOY.json","view_paper":"https://pith.science/paper/Z6SZVBWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.08948&json=true","fetch_graph":"https://pith.science/api/pith-number/Z6SZVBWY3WF3SFPCI4RXRYMOOY/graph.json","fetch_events":"https://pith.science/api/pith-number/Z6SZVBWY3WF3SFPCI4RXRYMOOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z6SZVBWY3WF3SFPCI4RXRYMOOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z6SZVBWY3WF3SFPCI4RXRYMOOY/action/storage_attestation","attest_author":"https://pith.science/pith/Z6SZVBWY3WF3SFPCI4RXRYMOOY/action/author_attestation","sign_citation":"https://pith.science/pith/Z6SZVBWY3WF3SFPCI4RXRYMOOY/action/citation_signature","submit_replication":"https://pith.science/pith/Z6SZVBWY3WF3SFPCI4RXRYMOOY/action/replication_record"}},"created_at":"2026-05-17T23:58:14.261394+00:00","updated_at":"2026-05-17T23:58:14.261394+00:00"}