{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7MJC5DIQMTQHJMHXZ5EKGYNAFZ","short_pith_number":"pith:7MJC5DIQ","canonical_record":{"source":{"id":"1905.01072","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-03T08:38:35Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"232844ee814d4d8211b483b08084bfa5a5b7c9e9e547c57cc018c9fd7c17355e","abstract_canon_sha256":"399b8eeef9cd49bd260902a6d827c6e919cee2242aeb9750e674850c9561302e"},"schema_version":"1.0"},"canonical_sha256":"fb122e8d1064e074b0f7cf48a361a02e49fd4d7000e0a92659807afd834dd6d2","source":{"kind":"arxiv","id":"1905.01072","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01072","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01072v3","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01072","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"pith_short_12","alias_value":"7MJC5DIQMTQH","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"pith_short_16","alias_value":"7MJC5DIQMTQHJMHX","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"pith_short_8","alias_value":"7MJC5DIQ","created_at":"2026-07-05T00:35:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7MJC5DIQMTQHJMHXZ5EKGYNAFZ","target":"record","payload":{"canonical_record":{"source":{"id":"1905.01072","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-03T08:38:35Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"232844ee814d4d8211b483b08084bfa5a5b7c9e9e547c57cc018c9fd7c17355e","abstract_canon_sha256":"399b8eeef9cd49bd260902a6d827c6e919cee2242aeb9750e674850c9561302e"},"schema_version":"1.0"},"canonical_sha256":"fb122e8d1064e074b0f7cf48a361a02e49fd4d7000e0a92659807afd834dd6d2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:25.766061Z","signature_b64":"OZKzjZlBE28id8iplkGsK4+/KySiG3OYSx6TCUtcH2Dmr59cD5ZRTrcvqHzMcGYSmnl759KvRo2rEJi3dCWrDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb122e8d1064e074b0f7cf48a361a02e49fd4d7000e0a92659807afd834dd6d2","last_reissued_at":"2026-07-05T00:35:25.765487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:25.765487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.01072","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:35:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4bb+BfFXA6uQAMV/+3YTR7Hs2hBDS/xF8nLkIWH1oi2kaf3kMpyVFpkBn1TF5jYnqj5Vd7rTyWNWnz83Qr8EBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:30:11.897513Z"},"content_sha256":"249e25f483d228cadc3100377676a0013471ccf0e9c89730748cd9e2b0d8016a","schema_version":"1.0","event_id":"sha256:249e25f483d228cadc3100377676a0013471ccf0e9c89730748cd9e2b0d8016a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7MJC5DIQMTQHJMHXZ5EKGYNAFZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Residual Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Shangtong Zhang, Shimon Whiteson, Wendelin Boehmer","submitted_at":"2019-05-03T08:38:35Z","abstract_excerpt":"We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperforms vanilla DDPG in the DeepMind Control Suite benchmark. Moreover, we find the residual algorithm an effective approach to the distribution mismatch problem in model-based planning. Compared with the existing TD($k$) method, our residual-based method makes weaker assumptions about the model and yields a greater performance boost."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01072","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1905.01072/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:35:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"thoW+wEBaafiGcOn5yc9e8fIXS8ks7+Sv2R1EJP5c85fQW0Y/zUUyKg4kFvOaHq+6vcMQHZ5lfA65DAzRAg2Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:30:11.898035Z"},"content_sha256":"d8a55a663fb19eecbcdae920c23b0d447e11b15cc904e8a3c06fd2d8f091ca20","schema_version":"1.0","event_id":"sha256:d8a55a663fb19eecbcdae920c23b0d447e11b15cc904e8a3c06fd2d8f091ca20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7MJC5DIQMTQHJMHXZ5EKGYNAFZ/bundle.json","state_url":"https://pith.science/pith/7MJC5DIQMTQHJMHXZ5EKGYNAFZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7MJC5DIQMTQHJMHXZ5EKGYNAFZ/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":"2026-08-19T14:30:11Z","links":{"resolver":"https://pith.science/pith/7MJC5DIQMTQHJMHXZ5EKGYNAFZ","bundle":"https://pith.science/pith/7MJC5DIQMTQHJMHXZ5EKGYNAFZ/bundle.json","state":"https://pith.science/pith/7MJC5DIQMTQHJMHXZ5EKGYNAFZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7MJC5DIQMTQHJMHXZ5EKGYNAFZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7MJC5DIQMTQHJMHXZ5EKGYNAFZ","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":"399b8eeef9cd49bd260902a6d827c6e919cee2242aeb9750e674850c9561302e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-03T08:38:35Z","title_canon_sha256":"232844ee814d4d8211b483b08084bfa5a5b7c9e9e547c57cc018c9fd7c17355e"},"schema_version":"1.0","source":{"id":"1905.01072","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.01072","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"arxiv_version","alias_value":"1905.01072v3","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.01072","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"pith_short_12","alias_value":"7MJC5DIQMTQH","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"pith_short_16","alias_value":"7MJC5DIQMTQHJMHX","created_at":"2026-07-05T00:35:25Z"},{"alias_kind":"pith_short_8","alias_value":"7MJC5DIQ","created_at":"2026-07-05T00:35:25Z"}],"graph_snapshots":[{"event_id":"sha256:d8a55a663fb19eecbcdae920c23b0d447e11b15cc904e8a3c06fd2d8f091ca20","target":"graph","created_at":"2026-07-05T00:35:25Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1905.01072/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We revisit residual algorithms in both model-free and model-based reinforcement learning settings. We propose the bidirectional target network technique to stabilize residual algorithms, yielding a residual version of DDPG that significantly outperforms vanilla DDPG in the DeepMind Control Suite benchmark. Moreover, we find the residual algorithm an effective approach to the distribution mismatch problem in model-based planning. Compared with the existing TD($k$) method, our residual-based method makes weaker assumptions about the model and yields a greater performance boost.","authors_text":"Shangtong Zhang, Shimon Whiteson, Wendelin Boehmer","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-03T08:38:35Z","title":"Deep Residual Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.01072","kind":"arxiv","version":3},"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":"sha256:249e25f483d228cadc3100377676a0013471ccf0e9c89730748cd9e2b0d8016a","target":"record","created_at":"2026-07-05T00:35:25Z","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":"399b8eeef9cd49bd260902a6d827c6e919cee2242aeb9750e674850c9561302e","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-03T08:38:35Z","title_canon_sha256":"232844ee814d4d8211b483b08084bfa5a5b7c9e9e547c57cc018c9fd7c17355e"},"schema_version":"1.0","source":{"id":"1905.01072","kind":"arxiv","version":3}},"canonical_sha256":"fb122e8d1064e074b0f7cf48a361a02e49fd4d7000e0a92659807afd834dd6d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fb122e8d1064e074b0f7cf48a361a02e49fd4d7000e0a92659807afd834dd6d2","first_computed_at":"2026-07-05T00:35:25.765487Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:25.765487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OZKzjZlBE28id8iplkGsK4+/KySiG3OYSx6TCUtcH2Dmr59cD5ZRTrcvqHzMcGYSmnl759KvRo2rEJi3dCWrDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:25.766061Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.01072","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:249e25f483d228cadc3100377676a0013471ccf0e9c89730748cd9e2b0d8016a","sha256:d8a55a663fb19eecbcdae920c23b0d447e11b15cc904e8a3c06fd2d8f091ca20"],"state_sha256":"8d22688845fb888d9afffdf63a0cf2df3f4869b675d1c749bf13c744d40c4ed9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FfXB4LSsYMNIyTqPLTikHMMxmpMu5FHrbpwRy2ccuGHIK4WvdfKO0WK221JnTZE7MKQGwrbVgTnNvi4ivQopBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:30:11.903655Z","bundle_sha256":"4600aad81dd1b01d9ee3a2021040e9bb1cdb8c5132c9de1381f0444c0adf663e"}}