{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XDTZESDWPW6HGTOI3MWXPG74DA","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":"e0fdf928feb85d3ec64bdf0e3ca74bc803f72dfbf68313be649643c0f1b1fc14","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-10-01T17:00:25Z","title_canon_sha256":"6ff2801d8a3191615e1390b69538123e7297c8280656d888b00505312edb2823"},"schema_version":"1.0","source":{"id":"2110.00535","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.00535","created_at":"2026-07-05T03:58:54Z"},{"alias_kind":"arxiv_version","alias_value":"2110.00535v2","created_at":"2026-07-05T03:58:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.00535","created_at":"2026-07-05T03:58:54Z"},{"alias_kind":"pith_short_12","alias_value":"XDTZESDWPW6H","created_at":"2026-07-05T03:58:54Z"},{"alias_kind":"pith_short_16","alias_value":"XDTZESDWPW6HGTOI","created_at":"2026-07-05T03:58:54Z"},{"alias_kind":"pith_short_8","alias_value":"XDTZESDW","created_at":"2026-07-05T03:58:54Z"}],"graph_snapshots":[{"event_id":"sha256:eaa1320ea3c8c8e0d11597aa90035a2161016b52d7e94ada5ea7872b5c5b960e","target":"graph","created_at":"2026-07-05T03:58:54Z","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/2110.00535/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributional reinforcement learning (DRL) extends the value-based approach by approximating the full distribution over future returns instead of the mean only, providing a richer signal that leads to improved performances. Quantile Regression (QR) based methods like QR-DQN project arbitrary distributions into a parametric subset of staircase distributions by minimizing the 1-Wasserstein distance. However, due to biases in the gradients, the quantile regression loss is used instead for training, guaranteeing the same minimizer and enjoying unbiased gradients. Non-crossing constraints on the q","authors_text":"Alix Lh\\'eritier, Nicolas Bondoux","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-10-01T17:00:25Z","title":"A Cram\\'er Distance perspective on Quantile Regression based Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.00535","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":"sha256:0c2383e09a204eb91cd930da76607eff9d7990b3c157619f6acfe4457798d178","target":"record","created_at":"2026-07-05T03:58:54Z","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":"e0fdf928feb85d3ec64bdf0e3ca74bc803f72dfbf68313be649643c0f1b1fc14","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-10-01T17:00:25Z","title_canon_sha256":"6ff2801d8a3191615e1390b69538123e7297c8280656d888b00505312edb2823"},"schema_version":"1.0","source":{"id":"2110.00535","kind":"arxiv","version":2}},"canonical_sha256":"b8e79248767dbc734dc8db2d779bfc181fbbe226ccd0dfa9a836e42234b10c5f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8e79248767dbc734dc8db2d779bfc181fbbe226ccd0dfa9a836e42234b10c5f","first_computed_at":"2026-07-05T03:58:54.602771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:58:54.602771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Og6IO6gw2ZbXNAEVWV4FSZJo9stKkN2qcYBjxg2taV7idEzeJxJK8viyHOARVQGy8UkV8VwfiEEcBskL4gCDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:58:54.603245Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.00535","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0c2383e09a204eb91cd930da76607eff9d7990b3c157619f6acfe4457798d178","sha256:eaa1320ea3c8c8e0d11597aa90035a2161016b52d7e94ada5ea7872b5c5b960e"],"state_sha256":"39f0aa5d2f1436245eec789cbe070d6c27a697c6375270661d236acf388625f1"}