{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KZNURD66SRTLPW5XFURYGS2VDQ","short_pith_number":"pith:KZNURD66","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"},"canonical_sha256":"565b488fde9466b7dbb72d23834b551c03affb690d29d5a0a2c57661bd13a278","source":{"kind":"arxiv","id":"2304.14421","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14421","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14421v1","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14421","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"KZNURD66SRTL","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"KZNURD66SRTLPW5X","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"KZNURD66","created_at":"2026-07-05T06:05:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KZNURD66SRTLPW5XFURYGS2VDQ","target":"record","payload":{"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"},"canonical_sha256":"565b488fde9466b7dbb72d23834b551c03affb690d29d5a0a2c57661bd13a278","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"},"source_kind":"arxiv","source_id":"2304.14421","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0LekXLlHR+DdOlOQpXySRc720B1vHN5HUV6iMC/2GFYVAMPEJgjO4UzAAXeVL4zmNWfwebnDknWjWeKSrR/sBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T19:51:41.122107Z"},"content_sha256":"52457bd570c04e0c14a42fab14a9d8da2b3454a71ca7b37ca86d91829fe0cd50","schema_version":"1.0","event_id":"sha256:52457bd570c04e0c14a42fab14a9d8da2b3454a71ca7b37ca86d91829fe0cd50"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KZNURD66SRTLPW5XFURYGS2VDQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:05:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IeXg6YJpjJ2lX3SQs0ZssQtVGbkXf24uuZ1RIdnILmbDhTdSVkDXnL6pPsuEyIaE6nUrqMH12VIlpMXL8DiNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T19:51:41.122478Z"},"content_sha256":"e18fddbdbdf7143b6aff35a48638e40539f96b2d5c2a6238fd344503b1c2be47","schema_version":"1.0","event_id":"sha256:e18fddbdbdf7143b6aff35a48638e40539f96b2d5c2a6238fd344503b1c2be47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ/bundle.json","state_url":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KZNURD66SRTLPW5XFURYGS2VDQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-25T19:51:41Z","links":{"resolver":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ","bundle":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ/bundle.json","state":"https://pith.science/pith/KZNURD66SRTLPW5XFURYGS2VDQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KZNURD66SRTLPW5XFURYGS2VDQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KZNURD66SRTLPW5XFURYGS2VDQ","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":"39f36d7e29e23e32693d7203d8b46c1d0b2c23d6cdd34c5f9ca0cd5b367fec9c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T06:57:00Z","title_canon_sha256":"c206dbb2243d47401094543233aceb210cd7759c26228fc44f3445371b6324f4"},"schema_version":"1.0","source":{"id":"2304.14421","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14421","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14421v1","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14421","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"KZNURD66SRTL","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"KZNURD66SRTLPW5X","created_at":"2026-07-05T06:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"KZNURD66","created_at":"2026-07-05T06:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:e18fddbdbdf7143b6aff35a48638e40539f96b2d5c2a6238fd344503b1c2be47","target":"graph","created_at":"2026-07-05T06:05:04Z","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/2304.14421/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Eric Moulines, Kirill Fedyanin, Mastane Achab, Reda Alami, Yasser Abdelaziz Dahou Djilali","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T06:57:00Z","title":"One-Step Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14421","kind":"arxiv","version":1},"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":"sha256:52457bd570c04e0c14a42fab14a9d8da2b3454a71ca7b37ca86d91829fe0cd50","target":"record","created_at":"2026-07-05T06:05:04Z","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":"39f36d7e29e23e32693d7203d8b46c1d0b2c23d6cdd34c5f9ca0cd5b367fec9c","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-27T06:57:00Z","title_canon_sha256":"c206dbb2243d47401094543233aceb210cd7759c26228fc44f3445371b6324f4"},"schema_version":"1.0","source":{"id":"2304.14421","kind":"arxiv","version":1}},"canonical_sha256":"565b488fde9466b7dbb72d23834b551c03affb690d29d5a0a2c57661bd13a278","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"565b488fde9466b7dbb72d23834b551c03affb690d29d5a0a2c57661bd13a278","first_computed_at":"2026-07-05T06:05:04.668555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:05:04.668555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ur2Z094M9Vxz+ehuC481cBPBLhSUddowVx5wtIxA/y150g0/cS3UsWmeofw1Ha47WA2/D7zsy4iYIqc+ecr/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:05:04.668906Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14421","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52457bd570c04e0c14a42fab14a9d8da2b3454a71ca7b37ca86d91829fe0cd50","sha256:e18fddbdbdf7143b6aff35a48638e40539f96b2d5c2a6238fd344503b1c2be47"],"state_sha256":"54fc8157ffeb50bbed94bdcf5ab02a97a2d6b872aed6a949ff87345174b48ea0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+pYeHrHvoPnjs46DSFby+EWI/tf8bpqmEIecQK94oBwwhJX3INvPy7tliwQ6lUeMLbIEy95r3Bm/lW1c4t09Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T19:51:41.124619Z","bundle_sha256":"f9b56d0ed3a24adeb4e3e6bde1d4036803154c929deb506faeb5bfc2799b157f"}}