{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7AQKC4RX6BKW6X76CTJW3XGKRF","short_pith_number":"pith:7AQKC4RX","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"},"canonical_sha256":"f820a17237f0556f5ffe14d36ddcca89613678b03ebc9b5856dc71dd0b10bf11","source":{"kind":"arxiv","id":"1903.04193","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04193","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04193v2","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04193","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"7AQKC4RX6BKW","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7AQKC4RX6BKW6X76","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7AQKC4RX","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7AQKC4RX6BKW6X76CTJW3XGKRF","target":"record","payload":{"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"},"canonical_sha256":"f820a17237f0556f5ffe14d36ddcca89613678b03ebc9b5856dc71dd0b10bf11","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"},"source_kind":"arxiv","source_id":"1903.04193","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2rZSuK3zvibSo5RFscA0ACWUyoCSrk8cMKRyBJ9RgnZzcsC9IS7ViUC4vcVJyN9IheA/bTlOY3T8KtRhlQ37Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:56:51.408492Z"},"content_sha256":"c772be320a9ae0a96596a037d53a813610964aac9e6d619ce772abab461a7297","schema_version":"1.0","event_id":"sha256:c772be320a9ae0a96596a037d53a813610964aac9e6d619ce772abab461a7297"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7AQKC4RX6BKW6X76CTJW3XGKRF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:43:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zj6pXbnAoLXVywVVoQwCSgPUyXhsUFYQwj0GpHUCYK/x8kPNd+hb/ZVUwJbOuOepLO7V5j4PNpZpbPI/Xrg8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T20:56:51.408841Z"},"content_sha256":"71eb94c4649689aac387c58ae2824d2abd4d7d2fce575d0ec6085f6c95116fe6","schema_version":"1.0","event_id":"sha256:71eb94c4649689aac387c58ae2824d2abd4d7d2fce575d0ec6085f6c95116fe6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/bundle.json","state_url":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T20:56:51Z","links":{"resolver":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF","bundle":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/bundle.json","state":"https://pith.science/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7AQKC4RX6BKW6X76CTJW3XGKRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7AQKC4RX6BKW6X76CTJW3XGKRF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1862890d86add2c44f927f27df0cc8d4d4d9d8c729c953ad9f5d179b07fe0141","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-11T09:59:58Z","title_canon_sha256":"c4b3f1aa789f8cd0f3922f2a0d64d4c76fbb17260fbaf2cd046fd689173d121a"},"schema_version":"1.0","source":{"id":"1903.04193","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.04193","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"arxiv_version","alias_value":"1903.04193v2","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.04193","created_at":"2026-05-17T23:43:32Z"},{"alias_kind":"pith_short_12","alias_value":"7AQKC4RX6BKW","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"7AQKC4RX6BKW6X76","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"7AQKC4RX","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:71eb94c4649689aac387c58ae2824d2abd4d7d2fce575d0ec6085f6c95116fe6","target":"graph","created_at":"2026-05-17T23:43:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Ann Now\\'e, Denis Steckelmacher, Diederik M. Roijers, H\\'el\\`ene Plisnier","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-11T09:59:58Z","title":"Sample-Efficient Model-Free Reinforcement Learning with Off-Policy Critics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.04193","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c772be320a9ae0a96596a037d53a813610964aac9e6d619ce772abab461a7297","target":"record","created_at":"2026-05-17T23:43:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1862890d86add2c44f927f27df0cc8d4d4d9d8c729c953ad9f5d179b07fe0141","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-11T09:59:58Z","title_canon_sha256":"c4b3f1aa789f8cd0f3922f2a0d64d4c76fbb17260fbaf2cd046fd689173d121a"},"schema_version":"1.0","source":{"id":"1903.04193","kind":"arxiv","version":2}},"canonical_sha256":"f820a17237f0556f5ffe14d36ddcca89613678b03ebc9b5856dc71dd0b10bf11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f820a17237f0556f5ffe14d36ddcca89613678b03ebc9b5856dc71dd0b10bf11","first_computed_at":"2026-05-17T23:43:32.765032Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:32.765032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xDdR9fFCwX1ouhXSy+KEP+J0LRYtf16oyD3qzkwI4Iu6ZH5lS3xHjkPVw2UFiRFvs1p79gef0CbuGpNACY9aAw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:32.765427Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.04193","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c772be320a9ae0a96596a037d53a813610964aac9e6d619ce772abab461a7297","sha256:71eb94c4649689aac387c58ae2824d2abd4d7d2fce575d0ec6085f6c95116fe6"],"state_sha256":"6ace0cfeedaf1f58cedbbede2363427969c0a50bae849168e9e5dfea78457c00"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qamVsirimS+melqwN8sOr9uFEn7W+qcJu5831iAhyQInnKXBdYcvUFhfJgMPAajVZizJ3AhbspCJbOO/M5rcAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T20:56:51.411212Z","bundle_sha256":"83d813afe66ae30436ff93f06fa290868d6c824be4ed82b364e6c2878d4c79b5"}}