{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UJ3Y3J7UXZO3MKSGAY6USTEVEA","short_pith_number":"pith:UJ3Y3J7U","schema_version":"1.0","canonical_sha256":"a2778da7f4be5db62a46063d494c952036726f7e4b84d26531f09be4397e7c6e","source":{"kind":"arxiv","id":"2007.06437","version":2},"attestation_state":"computed","paper":{"title":"A Provably Efficient Sample Collection Strategy for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Matteo Pirotta, Michal Valko","submitted_at":"2020-07-13T15:17:35Z","abstract_excerpt":"One of the challenges in online reinforcement learning (RL) is that the agent needs to trade off the exploration of the environment and the exploitation of the samples to optimize its behavior. Whether we optimize for regret, sample complexity, state-space coverage or model estimation, we need to strike a different exploration-exploitation trade-off. In this paper, we propose to tackle the exploration-exploitation problem following a decoupled approach composed of: 1) An \"objective-specific\" algorithm that (adaptively) prescribes how many samples to collect at which states, as if it has access"},"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":"2007.06437","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-13T15:17:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"10973083bb9103f99ef41cc745c97ca7fcdcae7a0fddab2f3c18f03a46ad4601","abstract_canon_sha256":"1654926f9e2042d286054a96243f9e25cbf5970576c5f7421f5bc58f797acbf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:02.406217Z","signature_b64":"sWrl5W+ymfyL4h5ECTJ/OcyMIQTerW2YzOIbUOgAF8i3Gpa6tGrfQaETpQ/rXke2lTk+C2MNF561AJZPyuTTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2778da7f4be5db62a46063d494c952036726f7e4b84d26531f09be4397e7c6e","last_reissued_at":"2026-07-05T03:33:02.405818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:02.405818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Provably Efficient Sample Collection Strategy for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alessandro Lazaric, Jean Tarbouriech, Matteo Pirotta, Michal Valko","submitted_at":"2020-07-13T15:17:35Z","abstract_excerpt":"One of the challenges in online reinforcement learning (RL) is that the agent needs to trade off the exploration of the environment and the exploitation of the samples to optimize its behavior. Whether we optimize for regret, sample complexity, state-space coverage or model estimation, we need to strike a different exploration-exploitation trade-off. In this paper, we propose to tackle the exploration-exploitation problem following a decoupled approach composed of: 1) An \"objective-specific\" algorithm that (adaptively) prescribes how many samples to collect at which states, as if it has access"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.06437","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/2007.06437/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":"2007.06437","created_at":"2026-07-05T03:33:02.405878+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.06437v2","created_at":"2026-07-05T03:33:02.405878+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.06437","created_at":"2026-07-05T03:33:02.405878+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJ3Y3J7UXZO3","created_at":"2026-07-05T03:33:02.405878+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJ3Y3J7UXZO3MKSG","created_at":"2026-07-05T03:33:02.405878+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJ3Y3J7U","created_at":"2026-07-05T03:33:02.405878+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/UJ3Y3J7UXZO3MKSGAY6USTEVEA","json":"https://pith.science/pith/UJ3Y3J7UXZO3MKSGAY6USTEVEA.json","graph_json":"https://pith.science/api/pith-number/UJ3Y3J7UXZO3MKSGAY6USTEVEA/graph.json","events_json":"https://pith.science/api/pith-number/UJ3Y3J7UXZO3MKSGAY6USTEVEA/events.json","paper":"https://pith.science/paper/UJ3Y3J7U"},"agent_actions":{"view_html":"https://pith.science/pith/UJ3Y3J7UXZO3MKSGAY6USTEVEA","download_json":"https://pith.science/pith/UJ3Y3J7UXZO3MKSGAY6USTEVEA.json","view_paper":"https://pith.science/paper/UJ3Y3J7U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.06437&json=true","fetch_graph":"https://pith.science/api/pith-number/UJ3Y3J7UXZO3MKSGAY6USTEVEA/graph.json","fetch_events":"https://pith.science/api/pith-number/UJ3Y3J7UXZO3MKSGAY6USTEVEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJ3Y3J7UXZO3MKSGAY6USTEVEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJ3Y3J7UXZO3MKSGAY6USTEVEA/action/storage_attestation","attest_author":"https://pith.science/pith/UJ3Y3J7UXZO3MKSGAY6USTEVEA/action/author_attestation","sign_citation":"https://pith.science/pith/UJ3Y3J7UXZO3MKSGAY6USTEVEA/action/citation_signature","submit_replication":"https://pith.science/pith/UJ3Y3J7UXZO3MKSGAY6USTEVEA/action/replication_record"}},"created_at":"2026-07-05T03:33:02.405878+00:00","updated_at":"2026-07-05T03:33:02.405878+00:00"}