{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VJIDAVF2KHLZ7RXLY2XFFL3QTO","short_pith_number":"pith:VJIDAVF2","canonical_record":{"source":{"id":"2210.05262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-10-11T08:46:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fb8bbabb3bea7e3cea2afccd667475e449955e2aa7f10fbff52c094ef96747ca","abstract_canon_sha256":"d8af6a4873d4e3da2fad0b9f52fabf2034d6951316ca5ef0b7f091719d71f385"},"schema_version":"1.0"},"canonical_sha256":"aa503054ba51d79fc6ebc6ae52af709bad1250761049a2ba1dd4dc45875acd14","source":{"kind":"arxiv","id":"2210.05262","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05262","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05262v1","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05262","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"VJIDAVF2KHLZ","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"VJIDAVF2KHLZ7RXL","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"VJIDAVF2","created_at":"2026-07-05T05:05:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VJIDAVF2KHLZ7RXLY2XFFL3QTO","target":"record","payload":{"canonical_record":{"source":{"id":"2210.05262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-10-11T08:46:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"fb8bbabb3bea7e3cea2afccd667475e449955e2aa7f10fbff52c094ef96747ca","abstract_canon_sha256":"d8af6a4873d4e3da2fad0b9f52fabf2034d6951316ca5ef0b7f091719d71f385"},"schema_version":"1.0"},"canonical_sha256":"aa503054ba51d79fc6ebc6ae52af709bad1250761049a2ba1dd4dc45875acd14","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:05:14.850249Z","signature_b64":"01NUu1Xc1ISf1vCjiNbqHxw8YUzGn3oc4YAN3caUT2gSq+GVrQLXagigjvzjCBmUQ0bFgdPceMBzM36ruwrKBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa503054ba51d79fc6ebc6ae52af709bad1250761049a2ba1dd4dc45875acd14","last_reissued_at":"2026-07-05T05:05:14.849841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:05:14.849841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.05262","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":"2026-07-05T05:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8xVWBLGWmYW/Cu/RArB5wvbdt6HJLutd2aF4LhE0aZxoKmXGsnfOwtd1F6odMGikjamV7koQQRhVUMq9Iae3Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:46:45.280839Z"},"content_sha256":"a46b5541627c2e2a7b72d4728ca092c8771f83f3ea8cd41d35636af7d5710e98","schema_version":"1.0","event_id":"sha256:a46b5541627c2e2a7b72d4728ca092c8771f83f3ea8cd41d35636af7d5710e98"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VJIDAVF2KHLZ7RXLY2XFFL3QTO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Factors of Influence of the Overestimation Bias of Q-Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Julius Wagenbach, Matthia Sabatelli","submitted_at":"2022-10-11T08:46:05Z","abstract_excerpt":"We study whether the learning rate $\\alpha$, the discount factor $\\gamma$ and the reward signal $r$ have an influence on the overestimation bias of the Q-Learning algorithm. Our preliminary results in environments which are stochastic and that require the use of neural networks as function approximators, show that all three parameters influence overestimation significantly. By carefully tuning $\\alpha$ and $\\gamma$, and by using an exponential moving average of $r$ in Q-Learning's temporal difference target, we show that the algorithm can learn value estimates that are more accurate than the o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05262","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/2210.05262/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":"2026-07-05T05:05:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ibHdWFZCoZoTNPgKkdoDu6xh4vMgO4ZRzvuL0ItdzRzHhxi2cjU0y/OPOyruLDOjFX1puvLjtS2sVfDuzMY5BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T16:46:45.281337Z"},"content_sha256":"cd5c467b868ecf9172f6304e5716c1083e0dd9877dee3c38919d41209b5c21b9","schema_version":"1.0","event_id":"sha256:cd5c467b868ecf9172f6304e5716c1083e0dd9877dee3c38919d41209b5c21b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJIDAVF2KHLZ7RXLY2XFFL3QTO/bundle.json","state_url":"https://pith.science/pith/VJIDAVF2KHLZ7RXLY2XFFL3QTO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJIDAVF2KHLZ7RXLY2XFFL3QTO/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":"2026-08-07T16:46:45Z","links":{"resolver":"https://pith.science/pith/VJIDAVF2KHLZ7RXLY2XFFL3QTO","bundle":"https://pith.science/pith/VJIDAVF2KHLZ7RXLY2XFFL3QTO/bundle.json","state":"https://pith.science/pith/VJIDAVF2KHLZ7RXLY2XFFL3QTO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJIDAVF2KHLZ7RXLY2XFFL3QTO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VJIDAVF2KHLZ7RXLY2XFFL3QTO","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":"d8af6a4873d4e3da2fad0b9f52fabf2034d6951316ca5ef0b7f091719d71f385","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-10-11T08:46:05Z","title_canon_sha256":"fb8bbabb3bea7e3cea2afccd667475e449955e2aa7f10fbff52c094ef96747ca"},"schema_version":"1.0","source":{"id":"2210.05262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.05262","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"arxiv_version","alias_value":"2210.05262v1","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.05262","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_12","alias_value":"VJIDAVF2KHLZ","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_16","alias_value":"VJIDAVF2KHLZ7RXL","created_at":"2026-07-05T05:05:14Z"},{"alias_kind":"pith_short_8","alias_value":"VJIDAVF2","created_at":"2026-07-05T05:05:14Z"}],"graph_snapshots":[{"event_id":"sha256:cd5c467b868ecf9172f6304e5716c1083e0dd9877dee3c38919d41209b5c21b9","target":"graph","created_at":"2026-07-05T05:05:14Z","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/2210.05262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study whether the learning rate $\\alpha$, the discount factor $\\gamma$ and the reward signal $r$ have an influence on the overestimation bias of the Q-Learning algorithm. Our preliminary results in environments which are stochastic and that require the use of neural networks as function approximators, show that all three parameters influence overestimation significantly. By carefully tuning $\\alpha$ and $\\gamma$, and by using an exponential moving average of $r$ in Q-Learning's temporal difference target, we show that the algorithm can learn value estimates that are more accurate than the o","authors_text":"Julius Wagenbach, Matthia Sabatelli","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-10-11T08:46:05Z","title":"Factors of Influence of the Overestimation Bias of Q-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.05262","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:a46b5541627c2e2a7b72d4728ca092c8771f83f3ea8cd41d35636af7d5710e98","target":"record","created_at":"2026-07-05T05:05:14Z","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":"d8af6a4873d4e3da2fad0b9f52fabf2034d6951316ca5ef0b7f091719d71f385","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2022-10-11T08:46:05Z","title_canon_sha256":"fb8bbabb3bea7e3cea2afccd667475e449955e2aa7f10fbff52c094ef96747ca"},"schema_version":"1.0","source":{"id":"2210.05262","kind":"arxiv","version":1}},"canonical_sha256":"aa503054ba51d79fc6ebc6ae52af709bad1250761049a2ba1dd4dc45875acd14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa503054ba51d79fc6ebc6ae52af709bad1250761049a2ba1dd4dc45875acd14","first_computed_at":"2026-07-05T05:05:14.849841Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:05:14.849841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"01NUu1Xc1ISf1vCjiNbqHxw8YUzGn3oc4YAN3caUT2gSq+GVrQLXagigjvzjCBmUQ0bFgdPceMBzM36ruwrKBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:05:14.850249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.05262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a46b5541627c2e2a7b72d4728ca092c8771f83f3ea8cd41d35636af7d5710e98","sha256:cd5c467b868ecf9172f6304e5716c1083e0dd9877dee3c38919d41209b5c21b9"],"state_sha256":"333f93cc02230d9a206d125b7f7725a3194cd5b8cac87ac6a7d5af62063e355d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uX+lyqq9I9DxGkeCDZnQK/+aT2iafYrmu/n3ZU778HArzBVrVy69V3B8CzrUWgfC2LSY5I2vY5Jjj0JnykhiAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T16:46:45.289010Z","bundle_sha256":"80ffe2c81ed60fd313f0d358f5eed98d3981216d2e992ed684327976d3d2d00f"}}