{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CQZDWXOCKIF4KJJPB3LA3LDHLY","short_pith_number":"pith:CQZDWXOC","canonical_record":{"source":{"id":"2009.13780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-09-29T04:58:17Z","cross_cats_sorted":[],"title_canon_sha256":"d93bd59a720de41054bbc8c1accd1ed95905ca45300fb640171296a1da29082d","abstract_canon_sha256":"105f1c691936ddd281c80bc0f9a5f51f5f4d19577999128e2a753f1f28b1247b"},"schema_version":"1.0"},"canonical_sha256":"14323b5dc2520bc5252f0ed60dac675e35618b8592b0cff5ca88b57fa2694a09","source":{"kind":"arxiv","id":"2009.13780","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.13780","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"2009.13780v1","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13780","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"CQZDWXOCKIF4","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"CQZDWXOCKIF4KJJP","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"CQZDWXOC","created_at":"2026-07-05T01:38:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CQZDWXOCKIF4KJJPB3LA3LDHLY","target":"record","payload":{"canonical_record":{"source":{"id":"2009.13780","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-09-29T04:58:17Z","cross_cats_sorted":[],"title_canon_sha256":"d93bd59a720de41054bbc8c1accd1ed95905ca45300fb640171296a1da29082d","abstract_canon_sha256":"105f1c691936ddd281c80bc0f9a5f51f5f4d19577999128e2a753f1f28b1247b"},"schema_version":"1.0"},"canonical_sha256":"14323b5dc2520bc5252f0ed60dac675e35618b8592b0cff5ca88b57fa2694a09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:38:44.935784Z","signature_b64":"tZ1SU9xtiM1RLokc/Q9APm2/7CcNkuLmx/s98rUAbygpYGSixaHQhgikWzp3w+mUNpPzQdvZ6rZ9iiFCRw6vDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14323b5dc2520bc5252f0ed60dac675e35618b8592b0cff5ca88b57fa2694a09","last_reissued_at":"2026-07-05T01:38:44.935371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:38:44.935371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.13780","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":"2026-07-05T01:38:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U06SzmeG/+4/vdDfeFL8EzZ+mKKuu7a2nusx73uhXP5WSy8fXLXofJfhHDaWM9KfTVixE4DTbWLletLJ9XnaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:10:07.929565Z"},"content_sha256":"7f39aa2b6b349a18a3f35bf43f9f712d1012a05e09b2a47a9d6e7013c7101613","schema_version":"1.0","event_id":"sha256:7f39aa2b6b349a18a3f35bf43f9f712d1012a05e09b2a47a9d6e7013c7101613"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CQZDWXOCKIF4KJJPB3LA3LDHLY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross Learning in Deep Q-Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexander Vinel, Xing Wang","submitted_at":"2020-09-29T04:58:17Z","abstract_excerpt":"In this work, we propose a novel cross Q-learning algorithm, aim at alleviating the well-known overestimation problem in value-based reinforcement learning methods, particularly in the deep Q-networks where the overestimation is exaggerated by function approximation errors. Our algorithm builds on double Q-learning, by maintaining a set of parallel models and estimate the Q-value based on a randomly selected network, which leads to reduced overestimation bias as well as the variance. We provide empirical evidence on the advantages of our method by evaluating on some benchmark environment, the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13780","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2009.13780/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":"2026-07-05T01:38:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"25sBtoRERuRMurHCDHuqhee2bjnpg7iPVo2ifHPPTpJ30AIgw8DCuKtEoNCQ4KTa6W7mVDJrB/wTgYIeEXr/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T14:10:07.930736Z"},"content_sha256":"119f12aa70bd6cfc660bfda3fecde36b22a35b03d13957ac0a0776985a39556a","schema_version":"1.0","event_id":"sha256:119f12aa70bd6cfc660bfda3fecde36b22a35b03d13957ac0a0776985a39556a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQZDWXOCKIF4KJJPB3LA3LDHLY/bundle.json","state_url":"https://pith.science/pith/CQZDWXOCKIF4KJJPB3LA3LDHLY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQZDWXOCKIF4KJJPB3LA3LDHLY/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":"2026-08-07T14:10:07Z","links":{"resolver":"https://pith.science/pith/CQZDWXOCKIF4KJJPB3LA3LDHLY","bundle":"https://pith.science/pith/CQZDWXOCKIF4KJJPB3LA3LDHLY/bundle.json","state":"https://pith.science/pith/CQZDWXOCKIF4KJJPB3LA3LDHLY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQZDWXOCKIF4KJJPB3LA3LDHLY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CQZDWXOCKIF4KJJPB3LA3LDHLY","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":"105f1c691936ddd281c80bc0f9a5f51f5f4d19577999128e2a753f1f28b1247b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-09-29T04:58:17Z","title_canon_sha256":"d93bd59a720de41054bbc8c1accd1ed95905ca45300fb640171296a1da29082d"},"schema_version":"1.0","source":{"id":"2009.13780","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.13780","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"2009.13780v1","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13780","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"CQZDWXOCKIF4","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"CQZDWXOCKIF4KJJP","created_at":"2026-07-05T01:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"CQZDWXOC","created_at":"2026-07-05T01:38:44Z"}],"graph_snapshots":[{"event_id":"sha256:119f12aa70bd6cfc660bfda3fecde36b22a35b03d13957ac0a0776985a39556a","target":"graph","created_at":"2026-07-05T01:38:44Z","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/2009.13780/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this work, we propose a novel cross Q-learning algorithm, aim at alleviating the well-known overestimation problem in value-based reinforcement learning methods, particularly in the deep Q-networks where the overestimation is exaggerated by function approximation errors. Our algorithm builds on double Q-learning, by maintaining a set of parallel models and estimate the Q-value based on a randomly selected network, which leads to reduced overestimation bias as well as the variance. We provide empirical evidence on the advantages of our method by evaluating on some benchmark environment, the ","authors_text":"Alexander Vinel, Xing Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-09-29T04:58:17Z","title":"Cross Learning in Deep Q-Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13780","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":"sha256:7f39aa2b6b349a18a3f35bf43f9f712d1012a05e09b2a47a9d6e7013c7101613","target":"record","created_at":"2026-07-05T01:38:44Z","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":"105f1c691936ddd281c80bc0f9a5f51f5f4d19577999128e2a753f1f28b1247b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2020-09-29T04:58:17Z","title_canon_sha256":"d93bd59a720de41054bbc8c1accd1ed95905ca45300fb640171296a1da29082d"},"schema_version":"1.0","source":{"id":"2009.13780","kind":"arxiv","version":1}},"canonical_sha256":"14323b5dc2520bc5252f0ed60dac675e35618b8592b0cff5ca88b57fa2694a09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14323b5dc2520bc5252f0ed60dac675e35618b8592b0cff5ca88b57fa2694a09","first_computed_at":"2026-07-05T01:38:44.935371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:38:44.935371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tZ1SU9xtiM1RLokc/Q9APm2/7CcNkuLmx/s98rUAbygpYGSixaHQhgikWzp3w+mUNpPzQdvZ6rZ9iiFCRw6vDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:38:44.935784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.13780","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f39aa2b6b349a18a3f35bf43f9f712d1012a05e09b2a47a9d6e7013c7101613","sha256:119f12aa70bd6cfc660bfda3fecde36b22a35b03d13957ac0a0776985a39556a"],"state_sha256":"a720711840c44a6d46b01b681814cfce4eca767ac104950c22b6171d426a9247"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dGzBNaN3SYugsmyCj8ME8WcLOV8+cQjoSppvofuWbNlvmmcl3VpKZpA1A7APd4GdTSP8DzIR2XJf6wmUQvveBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T14:10:07.935986Z","bundle_sha256":"72a0a1e6a5d3b3acddb59f64e130419957852c4365676f3c7d2331237c7b264c"}}