{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:LBRS652FCKUEK2VHPUW35IHPU6","short_pith_number":"pith:LBRS652F","canonical_record":{"source":{"id":"2002.06487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-16T02:02:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70e4efdb517772df47c91ee3bfe6e3820a4aebc181367b789f6594a04d148190","abstract_canon_sha256":"c938efaa1a5b4ea60f567ded7b2485fece5f5c063cde5f84e825e7be3c083595"},"schema_version":"1.0"},"canonical_sha256":"58632f774512a8456aa77d2dbea0efa7a8e68c604195b9db5f775e601d8e84a5","source":{"kind":"arxiv","id":"2002.06487","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06487","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06487v2","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06487","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"LBRS652FCKUE","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"LBRS652FCKUEK2VH","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"LBRS652F","created_at":"2026-07-05T03:03:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:LBRS652FCKUEK2VHPUW35IHPU6","target":"record","payload":{"canonical_record":{"source":{"id":"2002.06487","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-16T02:02:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"70e4efdb517772df47c91ee3bfe6e3820a4aebc181367b789f6594a04d148190","abstract_canon_sha256":"c938efaa1a5b4ea60f567ded7b2485fece5f5c063cde5f84e825e7be3c083595"},"schema_version":"1.0"},"canonical_sha256":"58632f774512a8456aa77d2dbea0efa7a8e68c604195b9db5f775e601d8e84a5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:48.310680Z","signature_b64":"pl/uGheflfXi4XXnwM9/ni4JRySCzEBgLZmSE8ckPrdFixu5oxNKdHtdwx2Ss6HegrIPcbcDVmVhjGXwZcfpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58632f774512a8456aa77d2dbea0efa7a8e68c604195b9db5f775e601d8e84a5","last_reissued_at":"2026-07-05T03:03:48.310327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:48.310327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.06487","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":"2026-07-05T03:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zrEWwPfJXbsq0r7KMIYILMXbya+wPsCZgNGywioyhsbymzEZVivCDRmp/Ub6DBxZgDgmWPcpkzfMeWehbyyTCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:03.965402Z"},"content_sha256":"da45c2a87352db1c3f7e6791a2de8fbc764878237de2f78846dd46a85d6fa7ac","schema_version":"1.0","event_id":"sha256:da45c2a87352db1c3f7e6791a2de8fbc764878237de2f78846dd46a85d6fa7ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:LBRS652FCKUEK2VHPUW35IHPU6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alona Fyshe, Martha White, Qingfeng Lan, Yangchen Pan","submitted_at":"2020-02-16T02:02:23Z","abstract_excerpt":"Q-learning suffers from overestimation bias, because it approximates the maximum action value using the maximum estimated action value. Algorithms have been proposed to reduce overestimation bias, but we lack an understanding of how bias interacts with performance, and the extent to which existing algorithms mitigate bias. In this paper, we 1) highlight that the effect of overestimation bias on learning efficiency is environment-dependent; 2) propose a generalization of Q-learning, called \\emph{Maxmin Q-learning}, which provides a parameter to flexibly control bias; 3) show theoretically that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06487","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2002.06487/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":"2026-07-05T03:03:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EbrJfhGKAimyWJ9TraWswpJvZLDyNkcxb7Hu/d3/ehtC6Aj5aZeETKT7s8T/XX0enkjSAzhL8jVq/5rRndtuBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:45:03.965955Z"},"content_sha256":"aff02c6aab50d13aba66df49b91223f4b61b37bd2161c93122b0f03f04771a26","schema_version":"1.0","event_id":"sha256:aff02c6aab50d13aba66df49b91223f4b61b37bd2161c93122b0f03f04771a26"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LBRS652FCKUEK2VHPUW35IHPU6/bundle.json","state_url":"https://pith.science/pith/LBRS652FCKUEK2VHPUW35IHPU6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LBRS652FCKUEK2VHPUW35IHPU6/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":"2026-08-07T01:45:03Z","links":{"resolver":"https://pith.science/pith/LBRS652FCKUEK2VHPUW35IHPU6","bundle":"https://pith.science/pith/LBRS652FCKUEK2VHPUW35IHPU6/bundle.json","state":"https://pith.science/pith/LBRS652FCKUEK2VHPUW35IHPU6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LBRS652FCKUEK2VHPUW35IHPU6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LBRS652FCKUEK2VHPUW35IHPU6","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":"c938efaa1a5b4ea60f567ded7b2485fece5f5c063cde5f84e825e7be3c083595","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-16T02:02:23Z","title_canon_sha256":"70e4efdb517772df47c91ee3bfe6e3820a4aebc181367b789f6594a04d148190"},"schema_version":"1.0","source":{"id":"2002.06487","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.06487","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"arxiv_version","alias_value":"2002.06487v2","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.06487","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"pith_short_12","alias_value":"LBRS652FCKUE","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"pith_short_16","alias_value":"LBRS652FCKUEK2VH","created_at":"2026-07-05T03:03:48Z"},{"alias_kind":"pith_short_8","alias_value":"LBRS652F","created_at":"2026-07-05T03:03:48Z"}],"graph_snapshots":[{"event_id":"sha256:aff02c6aab50d13aba66df49b91223f4b61b37bd2161c93122b0f03f04771a26","target":"graph","created_at":"2026-07-05T03:03:48Z","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/2002.06487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Q-learning suffers from overestimation bias, because it approximates the maximum action value using the maximum estimated action value. Algorithms have been proposed to reduce overestimation bias, but we lack an understanding of how bias interacts with performance, and the extent to which existing algorithms mitigate bias. In this paper, we 1) highlight that the effect of overestimation bias on learning efficiency is environment-dependent; 2) propose a generalization of Q-learning, called \\emph{Maxmin Q-learning}, which provides a parameter to flexibly control bias; 3) show theoretically that ","authors_text":"Alona Fyshe, Martha White, Qingfeng Lan, Yangchen Pan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-16T02:02:23Z","title":"Maxmin Q-learning: Controlling the Estimation Bias of Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.06487","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:da45c2a87352db1c3f7e6791a2de8fbc764878237de2f78846dd46a85d6fa7ac","target":"record","created_at":"2026-07-05T03:03:48Z","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":"c938efaa1a5b4ea60f567ded7b2485fece5f5c063cde5f84e825e7be3c083595","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-16T02:02:23Z","title_canon_sha256":"70e4efdb517772df47c91ee3bfe6e3820a4aebc181367b789f6594a04d148190"},"schema_version":"1.0","source":{"id":"2002.06487","kind":"arxiv","version":2}},"canonical_sha256":"58632f774512a8456aa77d2dbea0efa7a8e68c604195b9db5f775e601d8e84a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58632f774512a8456aa77d2dbea0efa7a8e68c604195b9db5f775e601d8e84a5","first_computed_at":"2026-07-05T03:03:48.310327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:03:48.310327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pl/uGheflfXi4XXnwM9/ni4JRySCzEBgLZmSE8ckPrdFixu5oxNKdHtdwx2Ss6HegrIPcbcDVmVhjGXwZcfpAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:03:48.310680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.06487","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da45c2a87352db1c3f7e6791a2de8fbc764878237de2f78846dd46a85d6fa7ac","sha256:aff02c6aab50d13aba66df49b91223f4b61b37bd2161c93122b0f03f04771a26"],"state_sha256":"fdf3c9cc4ac895277e9eae1f1e3a7c729ecce5ad76e1a23388a8606ce3154ef6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x3LBtaPf8nynWIGBU6Hjw/9vbxaza1CR08RN5uG5M+EOvMIzf5dJ5X4ZyLUfPWb9fltoTCmKog0WVUFIFlgfAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:45:03.969426Z","bundle_sha256":"38d78d60cf6d3692ad2e0c5da78b3858598529f9715b184e9620cfeba2dba0d5"}}