{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IHDA6NLVNNYYEYLWYKJT64272M","short_pith_number":"pith:IHDA6NLV","schema_version":"1.0","canonical_sha256":"41c60f35756b71826176c2933f735fd32114768e3f402ea7e64ebc49e03999bc","source":{"kind":"arxiv","id":"1811.09013","version":2},"attestation_state":"computed","paper":{"title":"An Off-policy Policy Gradient Theorem Using Emphatic Weightings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ehsan Imani, Eric Graves, Martha White","submitted_at":"2018-11-22T03:58:11Z","abstract_excerpt":"Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence of the policy gradient theorem which provides a simplified form for the gradient. In off-policy learning, however, where the behaviour policy is not necessarily attempting to learn and follow the optimal policy for the given task, the existence of such a theorem has been elusive. In this work, we solve this open problem by providing the first off-policy pol"},"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":"1811.09013","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-22T03:58:11Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"048f4a0ba38dc33d23ef88b4261d66fec4c91ab89a0846c8a9383083f542d787","abstract_canon_sha256":"2b52702fdcb2c26169ce6e5b45fd441ea24bcd2d5d07845be42f572d2ccc99ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:53.576301Z","signature_b64":"cM3+/PZzj0xrhdWsihCWyaY/ngFTJup5HuRjCxIEdSTyvKA+3UeOWI8bH4YIy6MFo0uvRye9RcitlFFKPUuSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41c60f35756b71826176c2933f735fd32114768e3f402ea7e64ebc49e03999bc","last_reissued_at":"2026-05-17T23:42:53.575820Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:53.575820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Off-policy Policy Gradient Theorem Using Emphatic Weightings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ehsan Imani, Eric Graves, Martha White","submitted_at":"2018-11-22T03:58:11Z","abstract_excerpt":"Policy gradient methods are widely used for control in reinforcement learning, particularly for the continuous action setting. There have been a host of theoretically sound algorithms proposed for the on-policy setting, due to the existence of the policy gradient theorem which provides a simplified form for the gradient. In off-policy learning, however, where the behaviour policy is not necessarily attempting to learn and follow the optimal policy for the given task, the existence of such a theorem has been elusive. In this work, we solve this open problem by providing the first off-policy pol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.09013","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":""},"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":"1811.09013","created_at":"2026-05-17T23:42:53.575893+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.09013v2","created_at":"2026-05-17T23:42:53.575893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.09013","created_at":"2026-05-17T23:42:53.575893+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHDA6NLVNNYY","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHDA6NLVNNYYEYLW","created_at":"2026-05-18T12:32:28.185984+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHDA6NLV","created_at":"2026-05-18T12:32:28.185984+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/IHDA6NLVNNYYEYLWYKJT64272M","json":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M.json","graph_json":"https://pith.science/api/pith-number/IHDA6NLVNNYYEYLWYKJT64272M/graph.json","events_json":"https://pith.science/api/pith-number/IHDA6NLVNNYYEYLWYKJT64272M/events.json","paper":"https://pith.science/paper/IHDA6NLV"},"agent_actions":{"view_html":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M","download_json":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M.json","view_paper":"https://pith.science/paper/IHDA6NLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.09013&json=true","fetch_graph":"https://pith.science/api/pith-number/IHDA6NLVNNYYEYLWYKJT64272M/graph.json","fetch_events":"https://pith.science/api/pith-number/IHDA6NLVNNYYEYLWYKJT64272M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M/action/storage_attestation","attest_author":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M/action/author_attestation","sign_citation":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M/action/citation_signature","submit_replication":"https://pith.science/pith/IHDA6NLVNNYYEYLWYKJT64272M/action/replication_record"}},"created_at":"2026-05-17T23:42:53.575893+00:00","updated_at":"2026-05-17T23:42:53.575893+00:00"}