{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DFYHX5GHCR66W5YMJGGOXNETC6","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":"b44d2662f14508bc7f2d4d3cd5106ae418a15100916f7fac8703dd85c2c6dd37","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:55:16Z","title_canon_sha256":"51b9face8b8993c0c48601694f0a9aa4e114bffa44e54e415429912b3b98e5b6"},"schema_version":"1.0","source":{"id":"2010.14498","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.14498","created_at":"2026-07-05T03:25:11Z"},{"alias_kind":"arxiv_version","alias_value":"2010.14498v2","created_at":"2026-07-05T03:25:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14498","created_at":"2026-07-05T03:25:11Z"},{"alias_kind":"pith_short_12","alias_value":"DFYHX5GHCR66","created_at":"2026-07-05T03:25:11Z"},{"alias_kind":"pith_short_16","alias_value":"DFYHX5GHCR66W5YM","created_at":"2026-07-05T03:25:11Z"},{"alias_kind":"pith_short_8","alias_value":"DFYHX5GH","created_at":"2026-07-05T03:25:11Z"}],"graph_snapshots":[{"event_id":"sha256:877abced2f9a05e4d21e367dfeb5a9fd3d8d86a0676b378e08eda577ced5fd33","target":"graph","created_at":"2026-07-05T03:25:11Z","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/2010.14498/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We identify an implicit under-parameterization phenomenon in value-based deep RL methods that use bootstrapping: when value functions, approximated using deep neural networks, are trained with gradient descent using iterated regression onto target values generated by previous instances of the value network, more gradient updates decrease the expressivity of the current value network. We characterize this loss of expressivity via a drop in the rank of the learned value network features, and show that this typically corresponds to a performance drop. We demonstrate this phenomenon on Atari and G","authors_text":"Aviral Kumar, Dibya Ghosh, Rishabh Agarwal, Sergey Levine","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:55:16Z","title":"Implicit Under-Parameterization Inhibits Data-Efficient Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14498","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:e47d2044bf76a0f01ffc76a8e88de5dfb1c24712cca7c6f8c353cbc3428e75e9","target":"record","created_at":"2026-07-05T03:25:11Z","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":"b44d2662f14508bc7f2d4d3cd5106ae418a15100916f7fac8703dd85c2c6dd37","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T17:55:16Z","title_canon_sha256":"51b9face8b8993c0c48601694f0a9aa4e114bffa44e54e415429912b3b98e5b6"},"schema_version":"1.0","source":{"id":"2010.14498","kind":"arxiv","version":2}},"canonical_sha256":"19707bf4c7147deb770c498cebb49317b295e7ad543b1c7832dde18efc77ba16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19707bf4c7147deb770c498cebb49317b295e7ad543b1c7832dde18efc77ba16","first_computed_at":"2026-07-05T03:25:11.166812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:11.166812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R9X0MR0dEqkf46SanMI9RFGuxP9ZDujfLi+ptRcZCA+6bkVRXgkVIetjYSupuyEqSy0DSgUjnuZOdFnE7IngBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:11.167284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.14498","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e47d2044bf76a0f01ffc76a8e88de5dfb1c24712cca7c6f8c353cbc3428e75e9","sha256:877abced2f9a05e4d21e367dfeb5a9fd3d8d86a0676b378e08eda577ced5fd33"],"state_sha256":"d65783dbf7c58b68e13a8c0d7a9872f6e4432fa2b5490097be3952b6b0eb091f"}