{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BNISRJCMTQP75F7CC2VBNI3TUG","short_pith_number":"pith:BNISRJCM","canonical_record":{"source":{"id":"1901.09455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-27T22:56:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0b75f90db82ba9f2a58fcbe5ace08bfff93cdda5ef603b11d634301249f61c51","abstract_canon_sha256":"53e97d88bb3a616e50bc1ba6d441bac1c3b1c5c97c049633bd8d464e46612348"},"schema_version":"1.0"},"canonical_sha256":"0b5128a44c9c1ffe97e216aa16a373a1a90b0ce78995175d792caa3a02b7fef5","source":{"kind":"arxiv","id":"1901.09455","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09455","created_at":"2026-05-17T23:55:24Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09455v1","created_at":"2026-05-17T23:55:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09455","created_at":"2026-05-17T23:55:24Z"},{"alias_kind":"pith_short_12","alias_value":"BNISRJCMTQP7","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BNISRJCMTQP75F7C","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BNISRJCM","created_at":"2026-05-18T12:33:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BNISRJCMTQP75F7CC2VBNI3TUG","target":"record","payload":{"canonical_record":{"source":{"id":"1901.09455","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-27T22:56:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0b75f90db82ba9f2a58fcbe5ace08bfff93cdda5ef603b11d634301249f61c51","abstract_canon_sha256":"53e97d88bb3a616e50bc1ba6d441bac1c3b1c5c97c049633bd8d464e46612348"},"schema_version":"1.0"},"canonical_sha256":"0b5128a44c9c1ffe97e216aa16a373a1a90b0ce78995175d792caa3a02b7fef5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:24.696388Z","signature_b64":"JfiFpi7wRdfwo7IH51fbw18lRJTVtp1Fu/CdW1BUGbeZ7I8o48WxcTraursEvgFGqr1NgyAAWRTV5YQkVAcMDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b5128a44c9c1ffe97e216aa16a373a1a90b0ce78995175d792caa3a02b7fef5","last_reissued_at":"2026-05-17T23:55:24.695881Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:24.695881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.09455","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:55:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"woLN93S42kwEmAlXPJgGVIAAWEi98ZPDpnvhIt4O5/XhKF1YFNZyOmvop5r0kmdC/QL0d00qOXGq1bFzk6ZTBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T17:30:15.391818Z"},"content_sha256":"7d445e3739378cafa90f483b7491caae6a69ee53b64c9e9c0e6c9477f494f576","schema_version":"1.0","event_id":"sha256:7d445e3739378cafa90f483b7491caae6a69ee53b64c9e9c0e6c9477f494f576"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BNISRJCMTQP75F7CC2VBNI3TUG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Carles Gelada, Marc G. Bellemare","submitted_at":"2019-01-27T22:56:50Z","abstract_excerpt":"In this paper we revisit the method of off-policy corrections for reinforcement learning (COP-TD) pioneered by Hallak et al. (2017). Under this method, online updates to the value function are reweighted to avoid divergence issues typical of off-policy learning. While Hallak et al.'s solution is appealing, it cannot easily be transferred to nonlinear function approximation. First, it requires a projection step onto the probability simplex; second, even though the operator describing the expected behavior of the off-policy learning algorithm is convergent, it is not known to be a contraction ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09455","kind":"arxiv","version":1},"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":"2026-05-17T23:55:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FC815ESAioT1NRfQ6T1h3e4kw5hw/AuANvEt2ooK+o2JgUqj1WtqO7GKbVa1vCi9l24/n0FeQZIaQuMM/kO6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T17:30:15.392589Z"},"content_sha256":"a82721398748fce956fd10c2480f27fb399e8d4d982724a4445a938cde884a6f","schema_version":"1.0","event_id":"sha256:a82721398748fce956fd10c2480f27fb399e8d4d982724a4445a938cde884a6f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BNISRJCMTQP75F7CC2VBNI3TUG/bundle.json","state_url":"https://pith.science/pith/BNISRJCMTQP75F7CC2VBNI3TUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BNISRJCMTQP75F7CC2VBNI3TUG/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":"2026-05-29T17:30:15Z","links":{"resolver":"https://pith.science/pith/BNISRJCMTQP75F7CC2VBNI3TUG","bundle":"https://pith.science/pith/BNISRJCMTQP75F7CC2VBNI3TUG/bundle.json","state":"https://pith.science/pith/BNISRJCMTQP75F7CC2VBNI3TUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BNISRJCMTQP75F7CC2VBNI3TUG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BNISRJCMTQP75F7CC2VBNI3TUG","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":"53e97d88bb3a616e50bc1ba6d441bac1c3b1c5c97c049633bd8d464e46612348","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-27T22:56:50Z","title_canon_sha256":"0b75f90db82ba9f2a58fcbe5ace08bfff93cdda5ef603b11d634301249f61c51"},"schema_version":"1.0","source":{"id":"1901.09455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.09455","created_at":"2026-05-17T23:55:24Z"},{"alias_kind":"arxiv_version","alias_value":"1901.09455v1","created_at":"2026-05-17T23:55:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.09455","created_at":"2026-05-17T23:55:24Z"},{"alias_kind":"pith_short_12","alias_value":"BNISRJCMTQP7","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_16","alias_value":"BNISRJCMTQP75F7C","created_at":"2026-05-18T12:33:12Z"},{"alias_kind":"pith_short_8","alias_value":"BNISRJCM","created_at":"2026-05-18T12:33:12Z"}],"graph_snapshots":[{"event_id":"sha256:a82721398748fce956fd10c2480f27fb399e8d4d982724a4445a938cde884a6f","target":"graph","created_at":"2026-05-17T23:55:24Z","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":"In this paper we revisit the method of off-policy corrections for reinforcement learning (COP-TD) pioneered by Hallak et al. (2017). Under this method, online updates to the value function are reweighted to avoid divergence issues typical of off-policy learning. While Hallak et al.'s solution is appealing, it cannot easily be transferred to nonlinear function approximation. First, it requires a projection step onto the probability simplex; second, even though the operator describing the expected behavior of the off-policy learning algorithm is convergent, it is not known to be a contraction ma","authors_text":"Carles Gelada, Marc G. Bellemare","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-27T22:56:50Z","title":"Off-Policy Deep Reinforcement Learning by Bootstrapping the Covariate Shift"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.09455","kind":"arxiv","version":1},"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":"sha256:7d445e3739378cafa90f483b7491caae6a69ee53b64c9e9c0e6c9477f494f576","target":"record","created_at":"2026-05-17T23:55:24Z","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":"53e97d88bb3a616e50bc1ba6d441bac1c3b1c5c97c049633bd8d464e46612348","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-27T22:56:50Z","title_canon_sha256":"0b75f90db82ba9f2a58fcbe5ace08bfff93cdda5ef603b11d634301249f61c51"},"schema_version":"1.0","source":{"id":"1901.09455","kind":"arxiv","version":1}},"canonical_sha256":"0b5128a44c9c1ffe97e216aa16a373a1a90b0ce78995175d792caa3a02b7fef5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b5128a44c9c1ffe97e216aa16a373a1a90b0ce78995175d792caa3a02b7fef5","first_computed_at":"2026-05-17T23:55:24.695881Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:55:24.695881Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JfiFpi7wRdfwo7IH51fbw18lRJTVtp1Fu/CdW1BUGbeZ7I8o48WxcTraursEvgFGqr1NgyAAWRTV5YQkVAcMDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:55:24.696388Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.09455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d445e3739378cafa90f483b7491caae6a69ee53b64c9e9c0e6c9477f494f576","sha256:a82721398748fce956fd10c2480f27fb399e8d4d982724a4445a938cde884a6f"],"state_sha256":"cf2275c71068f935a2cd137af1509b05b15cb77ec7d05042a645c0164928341c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VO1d5QFouh8eqGyBNR+upBKDDsKiV/Fmy6PiAk2ZevuT2eAsI6cuPgf/Ts5tqVAziFNSAan7aqmJ+bSah9BqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T17:30:15.396449Z","bundle_sha256":"46e8fb69df692063cd0c6fe18ec7242df61aaac3576628bbf6561a03fcc4dfc3"}}