{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BVQT2WPERTZMD4UDIKBPVBKDLH","short_pith_number":"pith:BVQT2WPE","schema_version":"1.0","canonical_sha256":"0d613d59e48cf2c1f2834282fa854359fedd695f0dc3a3886163f91d4c229636","source":{"kind":"arxiv","id":"1906.09340","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Reinforcement Learning Techniques for Effective Policy Adoption and Validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Clement H. C. Leung, Nikki Lijing Kuang","submitted_at":"2019-06-21T21:45:58Z","abstract_excerpt":"Rewards and punishments in different forms are pervasive and present in a wide variety of decision-making scenarios. By observing the outcome of a sufficient number of repeated trials, one would gradually learn the value and usefulness of a particular policy or strategy. However, in a given environment, the outcomes resulting from different trials are subject to chance influence and variations. In learning about the usefulness of a given policy, significant costs are involved in systematically undertaking the sequential trials; therefore, in most learning episodes, one would wish to keep the c"},"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":"1906.09340","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-21T21:45:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6bac82a3fa64d3bfc1bd3585e5cbb90332e69c2d4a2ac20254dff8c08db71847","abstract_canon_sha256":"6dc2df134d2032ac2ee3ab888a6509f3a8a52d7b0462eca476f10c0340984a18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:38.428789Z","signature_b64":"pfhRlRV6tBYMpvCMTLQN4lrajGQSJI/VxbkWbgU9Cn8NdFGzqxgRrkAalDFZro018YnnUPsM860tNtzPFTUnBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d613d59e48cf2c1f2834282fa854359fedd695f0dc3a3886163f91d4c229636","last_reissued_at":"2026-05-17T23:42:38.428251Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:38.428251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Reinforcement Learning Techniques for Effective Policy Adoption and Validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Clement H. C. Leung, Nikki Lijing Kuang","submitted_at":"2019-06-21T21:45:58Z","abstract_excerpt":"Rewards and punishments in different forms are pervasive and present in a wide variety of decision-making scenarios. By observing the outcome of a sufficient number of repeated trials, one would gradually learn the value and usefulness of a particular policy or strategy. However, in a given environment, the outcomes resulting from different trials are subject to chance influence and variations. In learning about the usefulness of a given policy, significant costs are involved in systematically undertaking the sequential trials; therefore, in most learning episodes, one would wish to keep the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09340","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":"1906.09340","created_at":"2026-05-17T23:42:38.428339+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.09340v1","created_at":"2026-05-17T23:42:38.428339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09340","created_at":"2026-05-17T23:42:38.428339+00:00"},{"alias_kind":"pith_short_12","alias_value":"BVQT2WPERTZM","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"BVQT2WPERTZMD4UD","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"BVQT2WPE","created_at":"2026-05-18T12:33:12.712433+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/BVQT2WPERTZMD4UDIKBPVBKDLH","json":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH.json","graph_json":"https://pith.science/api/pith-number/BVQT2WPERTZMD4UDIKBPVBKDLH/graph.json","events_json":"https://pith.science/api/pith-number/BVQT2WPERTZMD4UDIKBPVBKDLH/events.json","paper":"https://pith.science/paper/BVQT2WPE"},"agent_actions":{"view_html":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH","download_json":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH.json","view_paper":"https://pith.science/paper/BVQT2WPE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.09340&json=true","fetch_graph":"https://pith.science/api/pith-number/BVQT2WPERTZMD4UDIKBPVBKDLH/graph.json","fetch_events":"https://pith.science/api/pith-number/BVQT2WPERTZMD4UDIKBPVBKDLH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/action/storage_attestation","attest_author":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/action/author_attestation","sign_citation":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/action/citation_signature","submit_replication":"https://pith.science/pith/BVQT2WPERTZMD4UDIKBPVBKDLH/action/replication_record"}},"created_at":"2026-05-17T23:42:38.428339+00:00","updated_at":"2026-05-17T23:42:38.428339+00:00"}