{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KZNURD66SRTLPW5XFURYGS2VDQ","short_pith_number":"pith:KZNURD66","schema_version":"1.0","canonical_sha256":"565b488fde9466b7dbb72d23834b551c03affb690d29d5a0a2c57661bd13a278","source":{"kind":"arxiv","id":"2304.14421","version":1},"attestation_state":"computed","paper":{"title":"One-Step Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Moulines, Kirill Fedyanin, Mastane Achab, Reda Alami, Yasser Abdelaziz Dahou Djilali","submitted_at":"2023-04-27T06:57:00Z","abstract_excerpt":"Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the agent goes beyond the limit of the expected value, to capture the underlying probability distribution of the return across all time steps. The set of DistrRL algorithms has led to improved empirical performance. Nevertheless, the theory of DistrRL is still not fully understood, especially in the control case. In this paper, we present the simpler one-step distributional reinforcement learning (OS-DistrRL) framework "},"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":"2304.14421","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T06:57:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c206dbb2243d47401094543233aceb210cd7759c26228fc44f3445371b6324f4","abstract_canon_sha256":"39f36d7e29e23e32693d7203d8b46c1d0b2c23d6cdd34c5f9ca0cd5b367fec9c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:05:04.668906Z","signature_b64":"Ur2Z094M9Vxz+ehuC481cBPBLhSUddowVx5wtIxA/y150g0/cS3UsWmeofw1Ha47WA2/D7zsy4iYIqc+ecr/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"565b488fde9466b7dbb72d23834b551c03affb690d29d5a0a2c57661bd13a278","last_reissued_at":"2026-07-05T06:05:04.668555Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:05:04.668555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One-Step Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Moulines, Kirill Fedyanin, Mastane Achab, Reda Alami, Yasser Abdelaziz Dahou Djilali","submitted_at":"2023-04-27T06:57:00Z","abstract_excerpt":"Reinforcement learning (RL) allows an agent interacting sequentially with an environment to maximize its long-term expected return. In the distributional RL (DistrRL) paradigm, the agent goes beyond the limit of the expected value, to capture the underlying probability distribution of the return across all time steps. The set of DistrRL algorithms has led to improved empirical performance. Nevertheless, the theory of DistrRL is still not fully understood, especially in the control case. In this paper, we present the simpler one-step distributional reinforcement learning (OS-DistrRL) framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14421","kind":"arxiv","version":1},"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/2304.14421/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":"2304.14421","created_at":"2026-07-05T06:05:04.668610+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14421v1","created_at":"2026-07-05T06:05:04.668610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14421","created_at":"2026-07-05T06:05:04.668610+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZNURD66SRTL","created_at":"2026-07-05T06:05:04.668610+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZNURD66SRTLPW5X","created_at":"2026-07-05T06:05:04.668610+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZNURD66","created_at":"2026-07-05T06:05:04.668610+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/KZNURD66SRTLPW5XFURYGS2VDQ","json":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ.json","graph_json":"https://pith.science/api/pith-number/KZNURD66SRTLPW5XFURYGS2VDQ/graph.json","events_json":"https://pith.science/api/pith-number/KZNURD66SRTLPW5XFURYGS2VDQ/events.json","paper":"https://pith.science/paper/KZNURD66"},"agent_actions":{"view_html":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ","download_json":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ.json","view_paper":"https://pith.science/paper/KZNURD66","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14421&json=true","fetch_graph":"https://pith.science/api/pith-number/KZNURD66SRTLPW5XFURYGS2VDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KZNURD66SRTLPW5XFURYGS2VDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ/action/storage_attestation","attest_author":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ/action/author_attestation","sign_citation":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ/action/citation_signature","submit_replication":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ/action/replication_record"}},"created_at":"2026-07-05T06:05:04.668610+00:00","updated_at":"2026-07-05T06:05:04.668610+00:00"}