{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NSQJECDNSEXFMWYH2VYOT35TJ2","short_pith_number":"pith:NSQJECDN","schema_version":"1.0","canonical_sha256":"6ca092086d912e565b07d570e9efb34e98994b4d78b6a229ec7fdb339be7f7e3","source":{"kind":"arxiv","id":"2502.02516","version":3},"attestation_state":"computed","paper":{"title":"Adaptive Exploration for Multi-Reward Multi-Policy Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Alessio Russo","submitted_at":"2025-02-04T17:35:51Z","abstract_excerpt":"We study the policy evaluation problem in an online multi-reward multi-policy discounted setting, where multiple reward functions must be evaluated simultaneously for different policies. We adopt an $(\\epsilon,\\delta)$-PAC perspective to achieve $\\epsilon$-accurate estimates with high confidence across finite or convex sets of rewards, a setting that has not been investigated in the literature. Building on prior work on Multi-Reward Best Policy Identification, we adapt the MR-NaS exploration scheme to jointly minimize sample complexity for evaluating different policies across different reward "},"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":"2502.02516","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-04T17:35:51Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"47961ac7e3b83c9de7e94b11510aee8b7b3c327bd81418b2b3fe3f21608cf020","abstract_canon_sha256":"941ba0c7a259d1fb885fe68066526876d114533a6141d800f8f16ed9a60a1242"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:44.106256Z","signature_b64":"IioAeOb19bwcr+C6fPuQJznXebLIIxL3CYQgVb1t3TtmGj0V0V781NAgjI3a6GxeSWpACx6NRtqV31/dgxSKDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ca092086d912e565b07d570e9efb34e98994b4d78b6a229ec7fdb339be7f7e3","last_reissued_at":"2026-07-05T11:54:44.105800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:44.105800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptive Exploration for Multi-Reward Multi-Policy Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Pacchiano, Alessio Russo","submitted_at":"2025-02-04T17:35:51Z","abstract_excerpt":"We study the policy evaluation problem in an online multi-reward multi-policy discounted setting, where multiple reward functions must be evaluated simultaneously for different policies. We adopt an $(\\epsilon,\\delta)$-PAC perspective to achieve $\\epsilon$-accurate estimates with high confidence across finite or convex sets of rewards, a setting that has not been investigated in the literature. Building on prior work on Multi-Reward Best Policy Identification, we adapt the MR-NaS exploration scheme to jointly minimize sample complexity for evaluating different policies across different reward "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02516","kind":"arxiv","version":3},"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/2502.02516/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":"2502.02516","created_at":"2026-07-05T11:54:44.105857+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02516v3","created_at":"2026-07-05T11:54:44.105857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02516","created_at":"2026-07-05T11:54:44.105857+00:00"},{"alias_kind":"pith_short_12","alias_value":"NSQJECDNSEXF","created_at":"2026-07-05T11:54:44.105857+00:00"},{"alias_kind":"pith_short_16","alias_value":"NSQJECDNSEXFMWYH","created_at":"2026-07-05T11:54:44.105857+00:00"},{"alias_kind":"pith_short_8","alias_value":"NSQJECDN","created_at":"2026-07-05T11:54:44.105857+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/NSQJECDNSEXFMWYH2VYOT35TJ2","json":"https://pith.science/pith/NSQJECDNSEXFMWYH2VYOT35TJ2.json","graph_json":"https://pith.science/api/pith-number/NSQJECDNSEXFMWYH2VYOT35TJ2/graph.json","events_json":"https://pith.science/api/pith-number/NSQJECDNSEXFMWYH2VYOT35TJ2/events.json","paper":"https://pith.science/paper/NSQJECDN"},"agent_actions":{"view_html":"https://pith.science/pith/NSQJECDNSEXFMWYH2VYOT35TJ2","download_json":"https://pith.science/pith/NSQJECDNSEXFMWYH2VYOT35TJ2.json","view_paper":"https://pith.science/paper/NSQJECDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02516&json=true","fetch_graph":"https://pith.science/api/pith-number/NSQJECDNSEXFMWYH2VYOT35TJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/NSQJECDNSEXFMWYH2VYOT35TJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NSQJECDNSEXFMWYH2VYOT35TJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NSQJECDNSEXFMWYH2VYOT35TJ2/action/storage_attestation","attest_author":"https://pith.science/pith/NSQJECDNSEXFMWYH2VYOT35TJ2/action/author_attestation","sign_citation":"https://pith.science/pith/NSQJECDNSEXFMWYH2VYOT35TJ2/action/citation_signature","submit_replication":"https://pith.science/pith/NSQJECDNSEXFMWYH2VYOT35TJ2/action/replication_record"}},"created_at":"2026-07-05T11:54:44.105857+00:00","updated_at":"2026-07-05T11:54:44.105857+00:00"}