{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7AQKC4RX6BKW6X76CTJW3XGKRF","short_pith_number":"pith:7AQKC4RX","schema_version":"1.0","canonical_sha256":"f820a17237f0556f5ffe14d36ddcca89613678b03ebc9b5856dc71dd0b10bf11","source":{"kind":"arxiv","id":"1903.04193","version":2},"attestation_state":"computed","paper":{"title":"Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Denis Steckelmacher, Diederik M. Roijers, H\\'el\\`ene Plisnier","submitted_at":"2019-03-11T09:59:58Z","abstract_excerpt":"Value-based reinforcement-learning algorithms provide state-of-the-art results in model-free discrete-action settings, and tend to outperform actor-critic algorithms. We argue that actor-critic algorithms are limited by their need for an on-policy critic. We propose Bootstrapped Dual Policy Iteration (BDPI), a novel model-free reinforcement-learning algorithm for continuous states and discrete actions, with an actor and several off-policy critics. Off-policy critics are compatible with experience replay, ensuring high sample-efficiency, without the need for off-policy corrections. The actor, b"},"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":"1903.04193","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-11T09:59:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c4b3f1aa789f8cd0f3922f2a0d64d4c76fbb17260fbaf2cd046fd689173d121a","abstract_canon_sha256":"1862890d86add2c44f927f27df0cc8d4d4d9d8c729c953ad9f5d179b07fe0141"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:32.765427Z","signature_b64":"xDdR9fFCwX1ouhXSy+KEP+J0LRYtf16oyD3qzkwI4Iu6ZH5lS3xHjkPVw2UFiRFvs1p79gef0CbuGpNACY9aAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f820a17237f0556f5ffe14d36ddcca89613678b03ebc9b5856dc71dd0b10bf11","last_reissued_at":"2026-05-17T23:43:32.765032Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:32.765032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Ann Now\\'e, Denis Steckelmacher, Diederik M. Roijers, H\\'el\\`ene Plisnier","submitted_at":"2019-03-11T09:59:58Z","abstract_excerpt":"Value-based reinforcement-learning algorithms provide state-of-the-art results in model-free discrete-action settings, and tend to outperform actor-critic algorithms. We argue that actor-critic algorithms are limited by their need for an on-policy critic. We propose Bootstrapped Dual Policy Iteration (BDPI), a novel model-free reinforcement-learning algorithm for continuous states and discrete actions, with an actor and several off-policy critics. Off-policy critics are compatible with experience replay, ensuring high sample-efficiency, without the need for off-policy corrections. The actor, b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04193","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":"1903.04193","created_at":"2026-05-17T23:43:32.765089+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.04193v2","created_at":"2026-05-17T23:43:32.765089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04193","created_at":"2026-05-17T23:43:32.765089+00:00"},{"alias_kind":"pith_short_12","alias_value":"7AQKC4RX6BKW","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_16","alias_value":"7AQKC4RX6BKW6X76","created_at":"2026-05-18T12:33:12.712433+00:00"},{"alias_kind":"pith_short_8","alias_value":"7AQKC4RX","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/7AQKC4RX6BKW6X76CTJW3XGKRF","json":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF.json","graph_json":"https://pith.science/api/pith-number/7AQKC4RX6BKW6X76CTJW3XGKRF/graph.json","events_json":"https://pith.science/api/pith-number/7AQKC4RX6BKW6X76CTJW3XGKRF/events.json","paper":"https://pith.science/paper/7AQKC4RX"},"agent_actions":{"view_html":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF","download_json":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF.json","view_paper":"https://pith.science/paper/7AQKC4RX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.04193&json=true","fetch_graph":"https://pith.science/api/pith-number/7AQKC4RX6BKW6X76CTJW3XGKRF/graph.json","fetch_events":"https://pith.science/api/pith-number/7AQKC4RX6BKW6X76CTJW3XGKRF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/action/storage_attestation","attest_author":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/action/author_attestation","sign_citation":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/action/citation_signature","submit_replication":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/action/replication_record"}},"created_at":"2026-05-17T23:43:32.765089+00:00","updated_at":"2026-05-17T23:43:32.765089+00:00"}