{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YWMDWIX7PRYT427OZF62VX6BRE","short_pith_number":"pith:YWMDWIX7","schema_version":"1.0","canonical_sha256":"c5983b22ff7c713e6beec97daadfc18922705cd0728cfe44bd181fbeef9425fa","source":{"kind":"arxiv","id":"1809.06040","version":1},"attestation_state":"computed","paper":{"title":"Multi-Player Bandits: A Trekking Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Manjesh K. Hanawal, Sumit J. Darak","submitted_at":"2018-09-17T06:29:43Z","abstract_excerpt":"We study stochastic multi-armed bandits with many players. The players do not know the number of players, cannot communicate with each other and if multiple players select a common arm they collide and none of them receive any reward. We consider the static scenario, where the number of players remains fixed, and the dynamic scenario, where the players enter and leave at any time. We provide algorithms based on a novel `trekking approach' that guarantees constant regret for the static case and sub-linear regret for the dynamic case with high probability. The trekking approach eliminates the ne"},"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":"1809.06040","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-17T06:29:43Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f829aac618c2e76f8be94a36e7830f2fa143f3ca91e67782a6b2a052ca626487","abstract_canon_sha256":"82fbf12a31442d9049f0aa0c3eda8778bff2ce3e1968e9fa7ee724549dc7e05c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:35.809413Z","signature_b64":"0B1jg6UR+ByCwSUtsf/ttKcGbCaq9YGTRvov8Lq5u7WYMdg4Cizo6zFb+u7OCgMURsh2aJzjKIRZVnJYcS6nDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5983b22ff7c713e6beec97daadfc18922705cd0728cfe44bd181fbeef9425fa","last_reissued_at":"2026-05-18T00:05:35.808876Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:35.808876Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Player Bandits: A Trekking Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Manjesh K. Hanawal, Sumit J. Darak","submitted_at":"2018-09-17T06:29:43Z","abstract_excerpt":"We study stochastic multi-armed bandits with many players. The players do not know the number of players, cannot communicate with each other and if multiple players select a common arm they collide and none of them receive any reward. We consider the static scenario, where the number of players remains fixed, and the dynamic scenario, where the players enter and leave at any time. We provide algorithms based on a novel `trekking approach' that guarantees constant regret for the static case and sub-linear regret for the dynamic case with high probability. The trekking approach eliminates the ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.06040","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":"1809.06040","created_at":"2026-05-18T00:05:35.808962+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.06040v1","created_at":"2026-05-18T00:05:35.808962+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.06040","created_at":"2026-05-18T00:05:35.808962+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWMDWIX7PRYT","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWMDWIX7PRYT427O","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWMDWIX7","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2306.04498","citing_title":"Near-Optimal Privacy-Preserving Learning for Max-Min Fair Multi-Agent Bandits","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YWMDWIX7PRYT427OZF62VX6BRE","json":"https://pith.science/pith/YWMDWIX7PRYT427OZF62VX6BRE.json","graph_json":"https://pith.science/api/pith-number/YWMDWIX7PRYT427OZF62VX6BRE/graph.json","events_json":"https://pith.science/api/pith-number/YWMDWIX7PRYT427OZF62VX6BRE/events.json","paper":"https://pith.science/paper/YWMDWIX7"},"agent_actions":{"view_html":"https://pith.science/pith/YWMDWIX7PRYT427OZF62VX6BRE","download_json":"https://pith.science/pith/YWMDWIX7PRYT427OZF62VX6BRE.json","view_paper":"https://pith.science/paper/YWMDWIX7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.06040&json=true","fetch_graph":"https://pith.science/api/pith-number/YWMDWIX7PRYT427OZF62VX6BRE/graph.json","fetch_events":"https://pith.science/api/pith-number/YWMDWIX7PRYT427OZF62VX6BRE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWMDWIX7PRYT427OZF62VX6BRE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWMDWIX7PRYT427OZF62VX6BRE/action/storage_attestation","attest_author":"https://pith.science/pith/YWMDWIX7PRYT427OZF62VX6BRE/action/author_attestation","sign_citation":"https://pith.science/pith/YWMDWIX7PRYT427OZF62VX6BRE/action/citation_signature","submit_replication":"https://pith.science/pith/YWMDWIX7PRYT427OZF62VX6BRE/action/replication_record"}},"created_at":"2026-05-18T00:05:35.808962+00:00","updated_at":"2026-05-18T00:05:35.808962+00:00"}