{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DIGFYNNPVXMEZRAMF3H4U4TWHC","short_pith_number":"pith:DIGFYNNP","schema_version":"1.0","canonical_sha256":"1a0c5c35afadd84cc40c2ecfca7276389fbcbd3ba8ff29792f9f8ed18a6a585d","source":{"kind":"arxiv","id":"2206.08781","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Economic Policy: A New Frontier?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","econ.GN","q-fin.EC"],"primary_cat":"cs.LG","authors_text":"Callum Rhys Tilbury","submitted_at":"2022-06-16T10:35:26Z","abstract_excerpt":"Agent-based computational economics is a field with a rich academic history, yet one which has struggled to enter mainstream policy design toolboxes, plagued by the challenges associated with representing a complex and dynamic reality. The field of Reinforcement Learning (RL), too, has a rich history, and has recently been at the centre of several exponential developments. Modern RL implementations have been able to achieve unprecedented levels of sophistication, handling previously unthinkable degrees of complexity. This review surveys the historical barriers of classical agent-based techniqu"},"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":"2206.08781","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-16T10:35:26Z","cross_cats_sorted":["cs.AI","cs.MA","econ.GN","q-fin.EC"],"title_canon_sha256":"28ac663b6d55a86664a8409a9b0d91eae22632d814661a7f37da1856d8e2c5fb","abstract_canon_sha256":"8c3493dfb93f08c78dbe3e0d62cfc19b223ab60cfd47f7a6c2d4a4464bac0298"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:49.110243Z","signature_b64":"g5kjmJ3MsQimb+XFxXZ3IxVE+/AzSAxL/AMkp6q62HKejUu/J2FjxPK8k0WSgiyse0bY5fu0C2zobZApdLq/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a0c5c35afadd84cc40c2ecfca7276389fbcbd3ba8ff29792f9f8ed18a6a585d","last_reissued_at":"2026-07-05T05:44:49.109870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:49.109870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Economic Policy: A New Frontier?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA","econ.GN","q-fin.EC"],"primary_cat":"cs.LG","authors_text":"Callum Rhys Tilbury","submitted_at":"2022-06-16T10:35:26Z","abstract_excerpt":"Agent-based computational economics is a field with a rich academic history, yet one which has struggled to enter mainstream policy design toolboxes, plagued by the challenges associated with representing a complex and dynamic reality. The field of Reinforcement Learning (RL), too, has a rich history, and has recently been at the centre of several exponential developments. Modern RL implementations have been able to achieve unprecedented levels of sophistication, handling previously unthinkable degrees of complexity. This review surveys the historical barriers of classical agent-based techniqu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.08781","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/2206.08781/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":"2206.08781","created_at":"2026-07-05T05:44:49.109928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.08781v2","created_at":"2026-07-05T05:44:49.109928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.08781","created_at":"2026-07-05T05:44:49.109928+00:00"},{"alias_kind":"pith_short_12","alias_value":"DIGFYNNPVXME","created_at":"2026-07-05T05:44:49.109928+00:00"},{"alias_kind":"pith_short_16","alias_value":"DIGFYNNPVXMEZRAM","created_at":"2026-07-05T05:44:49.109928+00:00"},{"alias_kind":"pith_short_8","alias_value":"DIGFYNNP","created_at":"2026-07-05T05:44:49.109928+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/DIGFYNNPVXMEZRAMF3H4U4TWHC","json":"https://pith.science/pith/DIGFYNNPVXMEZRAMF3H4U4TWHC.json","graph_json":"https://pith.science/api/pith-number/DIGFYNNPVXMEZRAMF3H4U4TWHC/graph.json","events_json":"https://pith.science/api/pith-number/DIGFYNNPVXMEZRAMF3H4U4TWHC/events.json","paper":"https://pith.science/paper/DIGFYNNP"},"agent_actions":{"view_html":"https://pith.science/pith/DIGFYNNPVXMEZRAMF3H4U4TWHC","download_json":"https://pith.science/pith/DIGFYNNPVXMEZRAMF3H4U4TWHC.json","view_paper":"https://pith.science/paper/DIGFYNNP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.08781&json=true","fetch_graph":"https://pith.science/api/pith-number/DIGFYNNPVXMEZRAMF3H4U4TWHC/graph.json","fetch_events":"https://pith.science/api/pith-number/DIGFYNNPVXMEZRAMF3H4U4TWHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DIGFYNNPVXMEZRAMF3H4U4TWHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DIGFYNNPVXMEZRAMF3H4U4TWHC/action/storage_attestation","attest_author":"https://pith.science/pith/DIGFYNNPVXMEZRAMF3H4U4TWHC/action/author_attestation","sign_citation":"https://pith.science/pith/DIGFYNNPVXMEZRAMF3H4U4TWHC/action/citation_signature","submit_replication":"https://pith.science/pith/DIGFYNNPVXMEZRAMF3H4U4TWHC/action/replication_record"}},"created_at":"2026-07-05T05:44:49.109928+00:00","updated_at":"2026-07-05T05:44:49.109928+00:00"}