{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:FJYL66US4HFG3M2NJEPUCIC6HS","short_pith_number":"pith:FJYL66US","canonical_record":{"source":{"id":"1901.07510","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T18:38:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"39eb4ecab650af2db5c7b2137fd06b46d58bcf5add559469102c79f51370f5ed","abstract_canon_sha256":"5a142493d6f25bb0508e24d7ffb4c17d69001b46fcd056c677b638a79e48c6f0"},"schema_version":"1.0"},"canonical_sha256":"2a70bf7a92e1ca6db34d491f41205e3cb49b6f7638595013b645067ecc5a02bf","source":{"kind":"arxiv","id":"1901.07510","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07510","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07510v2","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07510","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"pith_short_12","alias_value":"FJYL66US4HFG","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FJYL66US4HFG3M2N","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FJYL66US","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:FJYL66US4HFG3M2NJEPUCIC6HS","target":"record","payload":{"canonical_record":{"source":{"id":"1901.07510","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T18:38:04Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"39eb4ecab650af2db5c7b2137fd06b46d58bcf5add559469102c79f51370f5ed","abstract_canon_sha256":"5a142493d6f25bb0508e24d7ffb4c17d69001b46fcd056c677b638a79e48c6f0"},"schema_version":"1.0"},"canonical_sha256":"2a70bf7a92e1ca6db34d491f41205e3cb49b6f7638595013b645067ecc5a02bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:31.376889Z","signature_b64":"4vguKI9VWItubLH+SuKF2WkUzUTvmSRW5qd/cGyPGBxM7CGDSrxJw3XxtDvelQS3ay+Oc3jvLjzINYt1RfuwAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a70bf7a92e1ca6db34d491f41205e3cb49b6f7638595013b645067ecc5a02bf","last_reissued_at":"2026-05-17T23:54:31.376182Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:31.376182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1901.07510","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":"2026-05-17T23:54:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1aHg3U4qUOmUXaBl4bGzZjrMZsyExN9EchmdI9os7dhhNFwmZ3LLEatF5/pFVqUvi1P1vJpPPFMbQD8TwkL5BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:48:57.789623Z"},"content_sha256":"4ecd8eb26deec1db0446f6f50af928396d158c1f050b7d36bbdb59711ed08604","schema_version":"1.0","event_id":"sha256:4ecd8eb26deec1db0446f6f50af928396d158c1f050b7d36bbdb59711ed08604"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:FJYL66US4HFG3M2NJEPUCIC6HS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"J. Fernando Hernandez-Garcia, Richard S. Sutton","submitted_at":"2019-01-22T18:38:04Z","abstract_excerpt":"Multi-step methods such as Retrace($\\lambda$) and $n$-step $Q$-learning have become a crucial component of modern deep reinforcement learning agents. These methods are often evaluated as a part of bigger architectures and their evaluations rarely include enough samples to draw statistically significant conclusions about their performance. This type of methodology makes it difficult to understand how particular algorithmic details of multi-step methods influence learning. In this paper we combine the $n$-step action-value algorithms Retrace, $Q$-learning, Tree Backup, Sarsa, and $Q(\\sigma)$ wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07510","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":"2026-05-17T23:54:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TCNGbGsioTStjg9IirVTv+aNxLVoO0+3c9D+G+LarwU9A1lsttZNdHbUsZyrptT2UV7sFke5GKqTgdqnLv11CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T19:48:57.790448Z"},"content_sha256":"aa026f968c0d3c065005366ca138ad7ffea0ad6cc5a06449b7fb5231026c8267","schema_version":"1.0","event_id":"sha256:aa026f968c0d3c065005366ca138ad7ffea0ad6cc5a06449b7fb5231026c8267"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FJYL66US4HFG3M2NJEPUCIC6HS/bundle.json","state_url":"https://pith.science/pith/FJYL66US4HFG3M2NJEPUCIC6HS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FJYL66US4HFG3M2NJEPUCIC6HS/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":"2026-05-31T19:48:57Z","links":{"resolver":"https://pith.science/pith/FJYL66US4HFG3M2NJEPUCIC6HS","bundle":"https://pith.science/pith/FJYL66US4HFG3M2NJEPUCIC6HS/bundle.json","state":"https://pith.science/pith/FJYL66US4HFG3M2NJEPUCIC6HS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FJYL66US4HFG3M2NJEPUCIC6HS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:FJYL66US4HFG3M2NJEPUCIC6HS","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":"5a142493d6f25bb0508e24d7ffb4c17d69001b46fcd056c677b638a79e48c6f0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T18:38:04Z","title_canon_sha256":"39eb4ecab650af2db5c7b2137fd06b46d58bcf5add559469102c79f51370f5ed"},"schema_version":"1.0","source":{"id":"1901.07510","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.07510","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"arxiv_version","alias_value":"1901.07510v2","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.07510","created_at":"2026-05-17T23:54:31Z"},{"alias_kind":"pith_short_12","alias_value":"FJYL66US4HFG","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"FJYL66US4HFG3M2N","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"FJYL66US","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:aa026f968c0d3c065005366ca138ad7ffea0ad6cc5a06449b7fb5231026c8267","target":"graph","created_at":"2026-05-17T23:54:31Z","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":"Multi-step methods such as Retrace($\\lambda$) and $n$-step $Q$-learning have become a crucial component of modern deep reinforcement learning agents. These methods are often evaluated as a part of bigger architectures and their evaluations rarely include enough samples to draw statistically significant conclusions about their performance. This type of methodology makes it difficult to understand how particular algorithmic details of multi-step methods influence learning. In this paper we combine the $n$-step action-value algorithms Retrace, $Q$-learning, Tree Backup, Sarsa, and $Q(\\sigma)$ wit","authors_text":"J. Fernando Hernandez-Garcia, Richard S. Sutton","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T18:38:04Z","title":"Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.07510","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":"sha256:4ecd8eb26deec1db0446f6f50af928396d158c1f050b7d36bbdb59711ed08604","target":"record","created_at":"2026-05-17T23:54:31Z","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":"5a142493d6f25bb0508e24d7ffb4c17d69001b46fcd056c677b638a79e48c6f0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-22T18:38:04Z","title_canon_sha256":"39eb4ecab650af2db5c7b2137fd06b46d58bcf5add559469102c79f51370f5ed"},"schema_version":"1.0","source":{"id":"1901.07510","kind":"arxiv","version":2}},"canonical_sha256":"2a70bf7a92e1ca6db34d491f41205e3cb49b6f7638595013b645067ecc5a02bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a70bf7a92e1ca6db34d491f41205e3cb49b6f7638595013b645067ecc5a02bf","first_computed_at":"2026-05-17T23:54:31.376182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:31.376182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4vguKI9VWItubLH+SuKF2WkUzUTvmSRW5qd/cGyPGBxM7CGDSrxJw3XxtDvelQS3ay+Oc3jvLjzINYt1RfuwAg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:31.376889Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.07510","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ecd8eb26deec1db0446f6f50af928396d158c1f050b7d36bbdb59711ed08604","sha256:aa026f968c0d3c065005366ca138ad7ffea0ad6cc5a06449b7fb5231026c8267"],"state_sha256":"ec6bf9834ca027290c9582d037805443cd0b0a682d0cb9fbec2e62fa02d2e201"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3F/+0gITby38AACT9cf2JPVAU3ynuNgfa9T+SOYTtwpmX9gwZC+A8jSPu4hY//WBQLVbHgqPDEWR2vDNrpf7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T19:48:57.795138Z","bundle_sha256":"29983f32a2f6365be83d5d5de109c68ebd11ce89d2b0f54af5d0dc5745abd481"}}