{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:IAA353B277NCIBAQ7BRJMBFHUW","short_pith_number":"pith:IAA353B2","canonical_record":{"source":{"id":"2303.13657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-03-23T20:27:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9018ed53c36cedde0a1e193c4bccfd5235b69e10fed95a17c9c300e563161ee2","abstract_canon_sha256":"2f07663389cd22dc735bea4065998924fe166b241d009b56a59b683c618bc541"},"schema_version":"1.0"},"canonical_sha256":"4001beec3affda240410f8629604a7a5b3b9b3f523f144464a4001bd2f88c5f7","source":{"kind":"arxiv","id":"2303.13657","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13657","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13657v1","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13657","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"pith_short_12","alias_value":"IAA353B277NC","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"pith_short_16","alias_value":"IAA353B277NCIBAQ","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"pith_short_8","alias_value":"IAA353B2","created_at":"2026-07-05T05:54:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:IAA353B277NCIBAQ7BRJMBFHUW","target":"record","payload":{"canonical_record":{"source":{"id":"2303.13657","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-03-23T20:27:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9018ed53c36cedde0a1e193c4bccfd5235b69e10fed95a17c9c300e563161ee2","abstract_canon_sha256":"2f07663389cd22dc735bea4065998924fe166b241d009b56a59b683c618bc541"},"schema_version":"1.0"},"canonical_sha256":"4001beec3affda240410f8629604a7a5b3b9b3f523f144464a4001bd2f88c5f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:17.610930Z","signature_b64":"zKP3ykkCDNkQZf8rutnaQmKomPSBXJG8b1/nA/pYffDZ/3PS0ZvAvLkmH0gMx6L+SJwboUVfu2uCr6txjMNMAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4001beec3affda240410f8629604a7a5b3b9b3f523f144464a4001bd2f88c5f7","last_reissued_at":"2026-07-05T05:54:17.610200Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:17.610200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.13657","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":"2026-07-05T05:54:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/sfacdS9nsCUPISe99yQG6vR7msUfhaqtkFVt7JlPLNkKDuRZ3tAFrUwole0RVKD01xHRvsm9FiT4cBlbyqVDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:20:00.070161Z"},"content_sha256":"6a7bad71da64852748a3520e48ccce1c125111eff17ac934e1e99812d4818f0a","schema_version":"1.0","event_id":"sha256:6a7bad71da64852748a3520e48ccce1c125111eff17ac934e1e99812d4818f0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:IAA353B277NCIBAQ7BRJMBFHUW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Evaluation in Distributional LQR","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"math.OC","authors_text":"Alessandro Abate, Karl H. Johansson, Michael M. Zavlanos, Siyi Wang, Yulong Gao, Zifan Wang","submitted_at":"2023-03-23T20:27:40Z","abstract_excerpt":"Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard RL. At the same time, a main challenge in DRL is that policy evaluation in DRL typically relies on the representation of the return distribution, which needs to be carefully designed. In this paper, we address this challenge for a special class of DRL problems that rely on linear quadratic regulator (LQR) for control, advocating for a new distributional approach to LQ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13657","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/2303.13657/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":"2026-07-05T05:54:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mwTrDCdZTAnhZ58imlOjkqKqAP6Rr2YITeNxZpMB9O/1eo58u83wbZH+zLYWK9UB4ROFJWrSLIEG5/zPoO9iCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T01:20:00.070697Z"},"content_sha256":"b60f6e499584beccc7d6d914d532570c6646883628cba9d662eb25177d23f185","schema_version":"1.0","event_id":"sha256:b60f6e499584beccc7d6d914d532570c6646883628cba9d662eb25177d23f185"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IAA353B277NCIBAQ7BRJMBFHUW/bundle.json","state_url":"https://pith.science/pith/IAA353B277NCIBAQ7BRJMBFHUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IAA353B277NCIBAQ7BRJMBFHUW/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":"2026-08-07T01:20:00Z","links":{"resolver":"https://pith.science/pith/IAA353B277NCIBAQ7BRJMBFHUW","bundle":"https://pith.science/pith/IAA353B277NCIBAQ7BRJMBFHUW/bundle.json","state":"https://pith.science/pith/IAA353B277NCIBAQ7BRJMBFHUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IAA353B277NCIBAQ7BRJMBFHUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IAA353B277NCIBAQ7BRJMBFHUW","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":"2f07663389cd22dc735bea4065998924fe166b241d009b56a59b683c618bc541","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-03-23T20:27:40Z","title_canon_sha256":"9018ed53c36cedde0a1e193c4bccfd5235b69e10fed95a17c9c300e563161ee2"},"schema_version":"1.0","source":{"id":"2303.13657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.13657","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"arxiv_version","alias_value":"2303.13657v1","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.13657","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"pith_short_12","alias_value":"IAA353B277NC","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"pith_short_16","alias_value":"IAA353B277NCIBAQ","created_at":"2026-07-05T05:54:17Z"},{"alias_kind":"pith_short_8","alias_value":"IAA353B2","created_at":"2026-07-05T05:54:17Z"}],"graph_snapshots":[{"event_id":"sha256:b60f6e499584beccc7d6d914d532570c6646883628cba9d662eb25177d23f185","target":"graph","created_at":"2026-07-05T05:54:17Z","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/2303.13657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Distributional reinforcement learning (DRL) enhances the understanding of the effects of the randomness in the environment by letting agents learn the distribution of a random return, rather than its expected value as in standard RL. At the same time, a main challenge in DRL is that policy evaluation in DRL typically relies on the representation of the return distribution, which needs to be carefully designed. In this paper, we address this challenge for a special class of DRL problems that rely on linear quadratic regulator (LQR) for control, advocating for a new distributional approach to LQ","authors_text":"Alessandro Abate, Karl H. Johansson, Michael M. Zavlanos, Siyi Wang, Yulong Gao, Zifan Wang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-03-23T20:27:40Z","title":"Policy Evaluation in Distributional LQR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.13657","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":"sha256:6a7bad71da64852748a3520e48ccce1c125111eff17ac934e1e99812d4818f0a","target":"record","created_at":"2026-07-05T05:54:17Z","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":"2f07663389cd22dc735bea4065998924fe166b241d009b56a59b683c618bc541","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.OC","submitted_at":"2023-03-23T20:27:40Z","title_canon_sha256":"9018ed53c36cedde0a1e193c4bccfd5235b69e10fed95a17c9c300e563161ee2"},"schema_version":"1.0","source":{"id":"2303.13657","kind":"arxiv","version":1}},"canonical_sha256":"4001beec3affda240410f8629604a7a5b3b9b3f523f144464a4001bd2f88c5f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4001beec3affda240410f8629604a7a5b3b9b3f523f144464a4001bd2f88c5f7","first_computed_at":"2026-07-05T05:54:17.610200Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:17.610200Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zKP3ykkCDNkQZf8rutnaQmKomPSBXJG8b1/nA/pYffDZ/3PS0ZvAvLkmH0gMx6L+SJwboUVfu2uCr6txjMNMAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:17.610930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.13657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a7bad71da64852748a3520e48ccce1c125111eff17ac934e1e99812d4818f0a","sha256:b60f6e499584beccc7d6d914d532570c6646883628cba9d662eb25177d23f185"],"state_sha256":"364c7462007f7c8e2c07b5e632a5edd0fbf088896fb46d34a8895d2d2584a305"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I8byniU54UEVbdrgU8bQwxidlrFZaH7nS/kGL+hp2G6/leC/Uhj+cThEbx1WqHFDW3efPxP2/5fjUsPGHPhvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T01:20:00.077158Z","bundle_sha256":"9431a0699e75e25a2a997765bc2679ce969aee56ec4d5611fa33935e140b3dbf"}}