{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MAP7RY3C3ITGYXJQSUV7CMAJGC","short_pith_number":"pith:MAP7RY3C","schema_version":"1.0","canonical_sha256":"601ff8e362da266c5d30952bf13009309251c6f69b0bf6146220052fca11034b","source":{"kind":"arxiv","id":"2104.09368","version":2},"attestation_state":"computed","paper":{"title":"Deep Reinforcement Learning in a Monetary Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["econ.GN","q-fin.EC","stat.ML"],"primary_cat":"econ.EM","authors_text":"Andreas Joseph, Michael Kumhof, Mingli Chen, Xinlei Pan, Xuan Zhou","submitted_at":"2021-04-19T14:56:44Z","abstract_excerpt":"We propose using deep reinforcement learning to solve dynamic stochastic general equilibrium models. Agents are represented by deep artificial neural networks and learn to solve their dynamic optimisation problem by interacting with the model environment, of which they have no a priori knowledge. Deep reinforcement learning offers a flexible yet principled way to model bounded rationality within this general class of models. We apply our proposed approach to a classical model from the adaptive learning literature in macroeconomics which looks at the interaction of monetary and fiscal policy. W"},"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":"2104.09368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2021-04-19T14:56:44Z","cross_cats_sorted":["econ.GN","q-fin.EC","stat.ML"],"title_canon_sha256":"b9d6723e74222c1438ab03c6ffbe4dea5e2c978dea26ba2450124dd75d3f4eab","abstract_canon_sha256":"3048a978035519881a1fc668f971389e2401eaa00c8524ffc390edc28b94d3cc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:30:41.529256Z","signature_b64":"CBF01k+9cYkXSLyUWM8oMekpC4cLSGhgzIKrgL0omKwJSeeViT5vwUybsiioZss8UklNoortmL2j+fSxCqpiCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"601ff8e362da266c5d30952bf13009309251c6f69b0bf6146220052fca11034b","last_reissued_at":"2026-07-05T05:30:41.528834Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:30:41.528834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Reinforcement Learning in a Monetary Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["econ.GN","q-fin.EC","stat.ML"],"primary_cat":"econ.EM","authors_text":"Andreas Joseph, Michael Kumhof, Mingli Chen, Xinlei Pan, Xuan Zhou","submitted_at":"2021-04-19T14:56:44Z","abstract_excerpt":"We propose using deep reinforcement learning to solve dynamic stochastic general equilibrium models. Agents are represented by deep artificial neural networks and learn to solve their dynamic optimisation problem by interacting with the model environment, of which they have no a priori knowledge. Deep reinforcement learning offers a flexible yet principled way to model bounded rationality within this general class of models. We apply our proposed approach to a classical model from the adaptive learning literature in macroeconomics which looks at the interaction of monetary and fiscal policy. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.09368","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/2104.09368/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":"2104.09368","created_at":"2026-07-05T05:30:41.528895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.09368v2","created_at":"2026-07-05T05:30:41.528895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.09368","created_at":"2026-07-05T05:30:41.528895+00:00"},{"alias_kind":"pith_short_12","alias_value":"MAP7RY3C3ITG","created_at":"2026-07-05T05:30:41.528895+00:00"},{"alias_kind":"pith_short_16","alias_value":"MAP7RY3C3ITGYXJQ","created_at":"2026-07-05T05:30:41.528895+00:00"},{"alias_kind":"pith_short_8","alias_value":"MAP7RY3C","created_at":"2026-07-05T05:30:41.528895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04741","citing_title":"Hierarchical Multiagent Reinforcement Learning for Multi-Group Tax Game","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04741","citing_title":"Hierarchical Multiagent Reinforcement Learning for Multi-Group Tax Game","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC","json":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC.json","graph_json":"https://pith.science/api/pith-number/MAP7RY3C3ITGYXJQSUV7CMAJGC/graph.json","events_json":"https://pith.science/api/pith-number/MAP7RY3C3ITGYXJQSUV7CMAJGC/events.json","paper":"https://pith.science/paper/MAP7RY3C"},"agent_actions":{"view_html":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC","download_json":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC.json","view_paper":"https://pith.science/paper/MAP7RY3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.09368&json=true","fetch_graph":"https://pith.science/api/pith-number/MAP7RY3C3ITGYXJQSUV7CMAJGC/graph.json","fetch_events":"https://pith.science/api/pith-number/MAP7RY3C3ITGYXJQSUV7CMAJGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/action/storage_attestation","attest_author":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/action/author_attestation","sign_citation":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/action/citation_signature","submit_replication":"https://pith.science/pith/MAP7RY3C3ITGYXJQSUV7CMAJGC/action/replication_record"}},"created_at":"2026-07-05T05:30:41.528895+00:00","updated_at":"2026-07-05T05:30:41.528895+00:00"}