{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:YPTCUJPR6WM2WLIVSDXRYWDZ6S","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":"51db457bcd5a9ff7b0a106a9b3422459228ee33507acb3d8d33d206429d1cab6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T04:56:04Z","title_canon_sha256":"c4bfe804e6597b707e9b6b38fbbf7169e7cec2e4ff49b6dad2fdb8c6f07516a0"},"schema_version":"1.0","source":{"id":"2210.03325","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.03325","created_at":"2026-07-05T05:04:18Z"},{"alias_kind":"arxiv_version","alias_value":"2210.03325v1","created_at":"2026-07-05T05:04:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03325","created_at":"2026-07-05T05:04:18Z"},{"alias_kind":"pith_short_12","alias_value":"YPTCUJPR6WM2","created_at":"2026-07-05T05:04:18Z"},{"alias_kind":"pith_short_16","alias_value":"YPTCUJPR6WM2WLIV","created_at":"2026-07-05T05:04:18Z"},{"alias_kind":"pith_short_8","alias_value":"YPTCUJPR","created_at":"2026-07-05T05:04:18Z"}],"graph_snapshots":[{"event_id":"sha256:4f2fe206d50d16d3f35efad2e6019a0fc6c830ef213e2bae0fe5720494d34bd3","target":"graph","created_at":"2026-07-05T05:04:18Z","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/2210.03325/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Q-Networks algorithm (DQN) was the first reinforcement learning algorithm using deep neural network to successfully surpass human level performance in a number of Atari learning environments. However, divergent and unstable behaviour have been long standing issues in DQNs. The unstable behaviour is often characterised by overestimation in the $Q$-values, commonly referred to as the overestimation bias. To address the overestimation bias and the divergent behaviour, a number of heuristic extensions have been proposed. Notably, multi-step updates have been shown to drastically reduce unstab","authors_text":"Adrian Ly, Francisco Cruz, Peter Vamplew, Richard Dazeley, Sunil Aryal","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T04:56:04Z","title":"Elastic Step DQN: A novel multi-step algorithm to alleviate overestimation in Deep QNetworks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03325","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:c152a8ae75708565c17d13d04995914922012f603b27ba328419bdc17bb4e690","target":"record","created_at":"2026-07-05T05:04:18Z","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":"51db457bcd5a9ff7b0a106a9b3422459228ee33507acb3d8d33d206429d1cab6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T04:56:04Z","title_canon_sha256":"c4bfe804e6597b707e9b6b38fbbf7169e7cec2e4ff49b6dad2fdb8c6f07516a0"},"schema_version":"1.0","source":{"id":"2210.03325","kind":"arxiv","version":1}},"canonical_sha256":"c3e62a25f1f599ab2d1590ef1c5879f4a7c084bc408ac784960a99208e2e57ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3e62a25f1f599ab2d1590ef1c5879f4a7c084bc408ac784960a99208e2e57ef","first_computed_at":"2026-07-05T05:04:18.739957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:18.739957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+8ADHLa+ahENA7xEEitKbkjLyRXDGOmMCjpkWQmBNAU23l8ea4fZ0c4LRRSLpggAP6zJLT+AdlgqGEbodb3hAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:18.740353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.03325","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c152a8ae75708565c17d13d04995914922012f603b27ba328419bdc17bb4e690","sha256:4f2fe206d50d16d3f35efad2e6019a0fc6c830ef213e2bae0fe5720494d34bd3"],"state_sha256":"abf936c385cbba2a033190df5e6c508dfa0fb35388a0664546fd998826f3e5e2"}