{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YLBBR7SHXNWNFXR7GQWGGXKQNB","short_pith_number":"pith:YLBBR7SH","schema_version":"1.0","canonical_sha256":"c2c218fe47bb6cd2de3f342c635d50684e2a1a07372080f7953e694b25c115b1","source":{"kind":"arxiv","id":"1802.08163","version":1},"attestation_state":"computed","paper":{"title":"An Analysis of Categorical Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Marc G. Bellemare, Mark Rowland, R\\'emi Munos, Will Dabney, Yee Whye Teh","submitted_at":"2018-02-22T16:50:08Z","abstract_excerpt":"Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yield state-of-the-art empirical performance. This was demonstrated by the recently proposed C51 algorithm, based on categorical distributional reinforcement learning (CDRL) [Bellemare et al., 2017]. However, the theoretical properties of CDRL algorithms are not yet well understood. In this paper, we introduce a framework to analyse CDRL algorithms, establish the importance of the projected distributional Bellman opera"},"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":"1802.08163","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-02-22T16:50:08Z","cross_cats_sorted":[],"title_canon_sha256":"91b55f76eb673dfea8a832abb45297817dc22ad468f2538aaa36cbca24b0ac43","abstract_canon_sha256":"0c3c2201c893ae583e57cdfd6dbab9af1a69ce4a72c7dcb31b93ececa4021c1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:45.364252Z","signature_b64":"14Uw4kJGyIYH0I4nP+RjmqqFbnYu29spAgIG/WrGMUirDcUsDS4zHuHpzK4j8anITNFbftu0g7UKTVziaG8bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2c218fe47bb6cd2de3f342c635d50684e2a1a07372080f7953e694b25c115b1","last_reissued_at":"2026-05-18T00:22:45.363808Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:45.363808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Analysis of Categorical Distributional Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Marc G. Bellemare, Mark Rowland, R\\'emi Munos, Will Dabney, Yee Whye Teh","submitted_at":"2018-02-22T16:50:08Z","abstract_excerpt":"Distributional approaches to value-based reinforcement learning model the entire distribution of returns, rather than just their expected values, and have recently been shown to yield state-of-the-art empirical performance. This was demonstrated by the recently proposed C51 algorithm, based on categorical distributional reinforcement learning (CDRL) [Bellemare et al., 2017]. However, the theoretical properties of CDRL algorithms are not yet well understood. In this paper, we introduce a framework to analyse CDRL algorithms, establish the importance of the projected distributional Bellman opera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.08163","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":""},"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":"1802.08163","created_at":"2026-05-18T00:22:45.363873+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.08163v1","created_at":"2026-05-18T00:22:45.363873+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.08163","created_at":"2026-05-18T00:22:45.363873+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLBBR7SHXNWN","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLBBR7SHXNWNFXR7","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLBBR7SH","created_at":"2026-05-18T12:33:04.347982+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/YLBBR7SHXNWNFXR7GQWGGXKQNB","json":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB.json","graph_json":"https://pith.science/api/pith-number/YLBBR7SHXNWNFXR7GQWGGXKQNB/graph.json","events_json":"https://pith.science/api/pith-number/YLBBR7SHXNWNFXR7GQWGGXKQNB/events.json","paper":"https://pith.science/paper/YLBBR7SH"},"agent_actions":{"view_html":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB","download_json":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB.json","view_paper":"https://pith.science/paper/YLBBR7SH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.08163&json=true","fetch_graph":"https://pith.science/api/pith-number/YLBBR7SHXNWNFXR7GQWGGXKQNB/graph.json","fetch_events":"https://pith.science/api/pith-number/YLBBR7SHXNWNFXR7GQWGGXKQNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/action/storage_attestation","attest_author":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/action/author_attestation","sign_citation":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/action/citation_signature","submit_replication":"https://pith.science/pith/YLBBR7SHXNWNFXR7GQWGGXKQNB/action/replication_record"}},"created_at":"2026-05-18T00:22:45.363873+00:00","updated_at":"2026-05-18T00:22:45.363873+00:00"}