{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7X7MQDU6QZU6DYDVE73M2E3QKA","short_pith_number":"pith:7X7MQDU6","schema_version":"1.0","canonical_sha256":"fdfec80e9e8669e1e07527f6cd1370500fdbeee97cf638fd70793bd31732719e","source":{"kind":"arxiv","id":"2007.13442","version":2},"attestation_state":"computed","paper":{"title":"Fast active learning for pure exploration in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Jonsson, Edouard Leurent, Emilie Kaufmann, Michal Valko, Omar Darwiche Domingues, Pierre M\\'enard","submitted_at":"2020-07-27T11:28:32Z","abstract_excerpt":"Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the agents may first choose to devote all their effort on exploring efficiently. The exploration remains a challenge while it has been addressed with many hand-tuned heuristics with different levels of generality on one side, and a few theoretically-backed exploration strategies on the other. Many of them are incarnated by intrinsic motivation and in particular explorations bonuses. A common rule of thumb for exploratio"},"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":"2007.13442","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-27T11:28:32Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"369f921769a5cedc716b71879b8b6e8de25dd4c72f0ef8ed73e5da6e514c1112","abstract_canon_sha256":"1d7f12aa1317dac13ca2aabae4824e0ab5ff1ee2513951623313b07effc9ce7b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:41:56.049039Z","signature_b64":"Rkoh4yJf9Bzo5ryZmOdTZIP3SvaNPfLYtXfQYhKPRGpvwGl8S7XLhRKT9fWDnvOR8cRduQcNuo4F1KInhezFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdfec80e9e8669e1e07527f6cd1370500fdbeee97cf638fd70793bd31732719e","last_reissued_at":"2026-07-05T01:41:56.048631Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:41:56.048631Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fast active learning for pure exploration in reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anders Jonsson, Edouard Leurent, Emilie Kaufmann, Michal Valko, Omar Darwiche Domingues, Pierre M\\'enard","submitted_at":"2020-07-27T11:28:32Z","abstract_excerpt":"Realistic environments often provide agents with very limited feedback. When the environment is initially unknown, the feedback, in the beginning, can be completely absent, and the agents may first choose to devote all their effort on exploring efficiently. The exploration remains a challenge while it has been addressed with many hand-tuned heuristics with different levels of generality on one side, and a few theoretically-backed exploration strategies on the other. Many of them are incarnated by intrinsic motivation and in particular explorations bonuses. A common rule of thumb for exploratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.13442","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/2007.13442/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":"2007.13442","created_at":"2026-07-05T01:41:56.048698+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.13442v2","created_at":"2026-07-05T01:41:56.048698+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.13442","created_at":"2026-07-05T01:41:56.048698+00:00"},{"alias_kind":"pith_short_12","alias_value":"7X7MQDU6QZU6","created_at":"2026-07-05T01:41:56.048698+00:00"},{"alias_kind":"pith_short_16","alias_value":"7X7MQDU6QZU6DYDV","created_at":"2026-07-05T01:41:56.048698+00:00"},{"alias_kind":"pith_short_8","alias_value":"7X7MQDU6","created_at":"2026-07-05T01:41:56.048698+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/7X7MQDU6QZU6DYDVE73M2E3QKA","json":"https://pith.science/pith/7X7MQDU6QZU6DYDVE73M2E3QKA.json","graph_json":"https://pith.science/api/pith-number/7X7MQDU6QZU6DYDVE73M2E3QKA/graph.json","events_json":"https://pith.science/api/pith-number/7X7MQDU6QZU6DYDVE73M2E3QKA/events.json","paper":"https://pith.science/paper/7X7MQDU6"},"agent_actions":{"view_html":"https://pith.science/pith/7X7MQDU6QZU6DYDVE73M2E3QKA","download_json":"https://pith.science/pith/7X7MQDU6QZU6DYDVE73M2E3QKA.json","view_paper":"https://pith.science/paper/7X7MQDU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.13442&json=true","fetch_graph":"https://pith.science/api/pith-number/7X7MQDU6QZU6DYDVE73M2E3QKA/graph.json","fetch_events":"https://pith.science/api/pith-number/7X7MQDU6QZU6DYDVE73M2E3QKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7X7MQDU6QZU6DYDVE73M2E3QKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7X7MQDU6QZU6DYDVE73M2E3QKA/action/storage_attestation","attest_author":"https://pith.science/pith/7X7MQDU6QZU6DYDVE73M2E3QKA/action/author_attestation","sign_citation":"https://pith.science/pith/7X7MQDU6QZU6DYDVE73M2E3QKA/action/citation_signature","submit_replication":"https://pith.science/pith/7X7MQDU6QZU6DYDVE73M2E3QKA/action/replication_record"}},"created_at":"2026-07-05T01:41:56.048698+00:00","updated_at":"2026-07-05T01:41:56.048698+00:00"}