{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PFXWRAG4CUZGU7A47XBJBR2HE3","short_pith_number":"pith:PFXWRAG4","schema_version":"1.0","canonical_sha256":"796f6880dc15326a7c1cfdc290c74726d52d19bc092f58f36711c4cc76d064f3","source":{"kind":"arxiv","id":"2306.07124","version":2},"attestation_state":"computed","paper":{"title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthijs T. J. Spaan, Moritz A. Zanger, Wendelin B\\\"ohmer","submitted_at":"2023-06-12T13:59:48Z","abstract_excerpt":"In contrast to classical reinforcement learning (RL), distributional RL algorithms aim to learn the distribution of returns rather than their expected value. Since the nature of the return distribution is generally unknown a priori or arbitrarily complex, a common approach finds approximations within a set of representable, parametric distributions. Typically, this involves a projection of the unconstrained distribution onto the set of simplified distributions. We argue that this projection step entails a strong inductive bias when coupled with neural networks and gradient descent, thereby pro"},"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":"2306.07124","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-12T13:59:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"65743b502a1f9bfc66ac04aea28ee3febfc7f03ec03018941237d42e8b7cfa91","abstract_canon_sha256":"db61199ba6257021eb89c7f5097359f151b04e7d219a66169a9ecf4c7832be58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:21.673281Z","signature_b64":"sSdHE9ByxsHQA5Lai6CeGhWH5+VrQvBtcIyNlYCQi8sKOCeNlbIdm+fctLjvndWLLFQmMhq2ncDmx6/NM0QGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"796f6880dc15326a7c1cfdc290c74726d52d19bc092f58f36711c4cc76d064f3","last_reissued_at":"2026-07-05T10:31:21.672660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:21.672660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diverse Projection Ensembles for Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Matthijs T. J. Spaan, Moritz A. Zanger, Wendelin B\\\"ohmer","submitted_at":"2023-06-12T13:59:48Z","abstract_excerpt":"In contrast to classical reinforcement learning (RL), distributional RL algorithms aim to learn the distribution of returns rather than their expected value. Since the nature of the return distribution is generally unknown a priori or arbitrarily complex, a common approach finds approximations within a set of representable, parametric distributions. Typically, this involves a projection of the unconstrained distribution onto the set of simplified distributions. We argue that this projection step entails a strong inductive bias when coupled with neural networks and gradient descent, thereby pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07124","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/2306.07124/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":"2306.07124","created_at":"2026-07-05T10:31:21.672730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.07124v2","created_at":"2026-07-05T10:31:21.672730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07124","created_at":"2026-07-05T10:31:21.672730+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFXWRAG4CUZG","created_at":"2026-07-05T10:31:21.672730+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFXWRAG4CUZGU7A4","created_at":"2026-07-05T10:31:21.672730+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFXWRAG4","created_at":"2026-07-05T10:31:21.672730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.03847","citing_title":"DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3","json":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3.json","graph_json":"https://pith.science/api/pith-number/PFXWRAG4CUZGU7A47XBJBR2HE3/graph.json","events_json":"https://pith.science/api/pith-number/PFXWRAG4CUZGU7A47XBJBR2HE3/events.json","paper":"https://pith.science/paper/PFXWRAG4"},"agent_actions":{"view_html":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3","download_json":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3.json","view_paper":"https://pith.science/paper/PFXWRAG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.07124&json=true","fetch_graph":"https://pith.science/api/pith-number/PFXWRAG4CUZGU7A47XBJBR2HE3/graph.json","fetch_events":"https://pith.science/api/pith-number/PFXWRAG4CUZGU7A47XBJBR2HE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/action/storage_attestation","attest_author":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/action/author_attestation","sign_citation":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/action/citation_signature","submit_replication":"https://pith.science/pith/PFXWRAG4CUZGU7A47XBJBR2HE3/action/replication_record"}},"created_at":"2026-07-05T10:31:21.672730+00:00","updated_at":"2026-07-05T10:31:21.672730+00:00"}