{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BP2DFI2HLJGFQA6GBPW23MLSTY","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":"0b41e730efa8311e6715487ae6e0f71cf55086ab52ff54f77aec909d95cbfc88","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T17:20:43Z","title_canon_sha256":"fc16d4b32943785fdfa9ae8e8f2dfad5a1336866a0a2a6b5ceb0fc2cc0ae4e42"},"schema_version":"1.0","source":{"id":"2501.13028","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.13028","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"arxiv_version","alias_value":"2501.13028v2","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13028","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"pith_short_12","alias_value":"BP2DFI2HLJGF","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"pith_short_16","alias_value":"BP2DFI2HLJGFQA6G","created_at":"2026-07-05T11:47:18Z"},{"alias_kind":"pith_short_8","alias_value":"BP2DFI2H","created_at":"2026-07-05T11:47:18Z"}],"graph_snapshots":[{"event_id":"sha256:f91d9dc11f08ab5d6b0fc588e97398c8c53d22ccfba920a11e84d77ab2a1c43c","target":"graph","created_at":"2026-07-05T11:47:18Z","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/2501.13028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andr\\'e Barreto, Bernardo \\'Avila Pires, David Abel, Diana Borsa, Khimya Khetarpal, Mark Rowland, R\\'emi Munos, Will Dabney, Zhaohan Daniel Guo","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T17:20:43Z","title":"Optimizing Return Distributions with Distributional Dynamic Programming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13028","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":"sha256:655916cb6f50d656da44d7e672ec3364bd94360e737abb7fe5a691ee5496e2d4","target":"record","created_at":"2026-07-05T11:47:18Z","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":"0b41e730efa8311e6715487ae6e0f71cf55086ab52ff54f77aec909d95cbfc88","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-22T17:20:43Z","title_canon_sha256":"fc16d4b32943785fdfa9ae8e8f2dfad5a1336866a0a2a6b5ceb0fc2cc0ae4e42"},"schema_version":"1.0","source":{"id":"2501.13028","kind":"arxiv","version":2}},"canonical_sha256":"0bf432a3475a4c5803c60bedadb1729e0c296b99f64328bb46e301c469224107","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0bf432a3475a4c5803c60bedadb1729e0c296b99f64328bb46e301c469224107","first_computed_at":"2026-07-05T11:47:18.076791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:47:18.076791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yz0tgj8k1k7QlcNQdHOjBYxwXHCvupU7tJ5pPTR9ybbTcvZhDplJuRwa7e/o0oFrefefz/DPDYPgI6J3Oc4nDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:47:18.077289Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.13028","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:655916cb6f50d656da44d7e672ec3364bd94360e737abb7fe5a691ee5496e2d4","sha256:f91d9dc11f08ab5d6b0fc588e97398c8c53d22ccfba920a11e84d77ab2a1c43c"],"state_sha256":"1f50f102e7f0db5d66a17185b953508d22a35d3ac4a2e6ead3db41441464fdfa"}