{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BP2DFI2HLJGFQA6GBPW23MLSTY","short_pith_number":"pith:BP2DFI2H","schema_version":"1.0","canonical_sha256":"0bf432a3475a4c5803c60bedadb1729e0c296b99f64328bb46e301c469224107","source":{"kind":"arxiv","id":"2501.13028","version":2},"attestation_state":"computed","paper":{"title":"Optimizing Return Distributions with Distributional Dynamic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Bernardo \\'Avila Pires, David Abel, Diana Borsa, Khimya Khetarpal, Mark Rowland, R\\'emi Munos, Will Dabney, Zhaohan Daniel Guo","submitted_at":"2025-01-22T17:20:43Z","abstract_excerpt":"We introduce distributional dynamic programming (DP) methods for optimizing statistical functionals of the return distribution, with standard reinforcement learning as a special case. Previous distributional DP methods could optimize the same class of expected utilities as classic DP. To go beyond, we combine distributional DP with stock augmentation, a technique previously introduced for classic DP in the context of risk-sensitive RL, where the MDP state is augmented with a statistic of the rewards obtained since the first time step. We find that a number of recently studied problems can be f"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.13028","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T17:20:43Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"fc16d4b32943785fdfa9ae8e8f2dfad5a1336866a0a2a6b5ceb0fc2cc0ae4e42","abstract_canon_sha256":"0b41e730efa8311e6715487ae6e0f71cf55086ab52ff54f77aec909d95cbfc88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:18.077289Z","signature_b64":"yz0tgj8k1k7QlcNQdHOjBYxwXHCvupU7tJ5pPTR9ybbTcvZhDplJuRwa7e/o0oFrefefz/DPDYPgI6J3Oc4nDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0bf432a3475a4c5803c60bedadb1729e0c296b99f64328bb46e301c469224107","last_reissued_at":"2026-07-05T11:47:18.076791Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:18.076791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Return Distributions with Distributional Dynamic Programming","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Andr\\'e Barreto, Bernardo \\'Avila Pires, David Abel, Diana Borsa, Khimya Khetarpal, Mark Rowland, R\\'emi Munos, Will Dabney, Zhaohan Daniel Guo","submitted_at":"2025-01-22T17:20:43Z","abstract_excerpt":"We introduce distributional dynamic programming (DP) methods for optimizing statistical functionals of the return distribution, with standard reinforcement learning as a special case. Previous distributional DP methods could optimize the same class of expected utilities as classic DP. To go beyond, we combine distributional DP with stock augmentation, a technique previously introduced for classic DP in the context of risk-sensitive RL, where the MDP state is augmented with a statistic of the rewards obtained since the first time step. We find that a number of recently studied problems can be f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13028","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/2501.13028/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.13028","created_at":"2026-07-05T11:47:18.076851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13028v2","created_at":"2026-07-05T11:47:18.076851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13028","created_at":"2026-07-05T11:47:18.076851+00:00"},{"alias_kind":"pith_short_12","alias_value":"BP2DFI2HLJGF","created_at":"2026-07-05T11:47:18.076851+00:00"},{"alias_kind":"pith_short_16","alias_value":"BP2DFI2HLJGFQA6G","created_at":"2026-07-05T11:47:18.076851+00:00"},{"alias_kind":"pith_short_8","alias_value":"BP2DFI2H","created_at":"2026-07-05T11:47:18.076851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BP2DFI2HLJGFQA6GBPW23MLSTY","json":"https://pith.science/pith/BP2DFI2HLJGFQA6GBPW23MLSTY.json","graph_json":"https://pith.science/api/pith-number/BP2DFI2HLJGFQA6GBPW23MLSTY/graph.json","events_json":"https://pith.science/api/pith-number/BP2DFI2HLJGFQA6GBPW23MLSTY/events.json","paper":"https://pith.science/paper/BP2DFI2H"},"agent_actions":{"view_html":"https://pith.science/pith/BP2DFI2HLJGFQA6GBPW23MLSTY","download_json":"https://pith.science/pith/BP2DFI2HLJGFQA6GBPW23MLSTY.json","view_paper":"https://pith.science/paper/BP2DFI2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13028&json=true","fetch_graph":"https://pith.science/api/pith-number/BP2DFI2HLJGFQA6GBPW23MLSTY/graph.json","fetch_events":"https://pith.science/api/pith-number/BP2DFI2HLJGFQA6GBPW23MLSTY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BP2DFI2HLJGFQA6GBPW23MLSTY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BP2DFI2HLJGFQA6GBPW23MLSTY/action/storage_attestation","attest_author":"https://pith.science/pith/BP2DFI2HLJGFQA6GBPW23MLSTY/action/author_attestation","sign_citation":"https://pith.science/pith/BP2DFI2HLJGFQA6GBPW23MLSTY/action/citation_signature","submit_replication":"https://pith.science/pith/BP2DFI2HLJGFQA6GBPW23MLSTY/action/replication_record"}},"created_at":"2026-07-05T11:47:18.076851+00:00","updated_at":"2026-07-05T11:47:18.076851+00:00"}