{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NQ7RTKXWE6GVOWQ6ZPEJPUDXQ3","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":"5408797d38b4eecb53e048d6580a1858921db6746ed0774b60ae0addf55a0914","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T20:20:27Z","title_canon_sha256":"5e391539e2107da15f11daa5317149c6548ba48e8333366fb0d91c8f61b30ae0"},"schema_version":"1.0","source":{"id":"1901.11084","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.11084","created_at":"2026-05-17T23:53:04Z"},{"alias_kind":"arxiv_version","alias_value":"1901.11084v2","created_at":"2026-05-17T23:53:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.11084","created_at":"2026-05-17T23:53:04Z"},{"alias_kind":"pith_short_12","alias_value":"NQ7RTKXWE6GV","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NQ7RTKXWE6GVOWQ6","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NQ7RTKXW","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:600d58ffce505415fa7204221d4e5e0782f8e9e797ad8582911f49a2442a742b","target":"graph","created_at":"2026-05-17T23:53:04Z","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"},"paper":{"abstract_excerpt":"Since their introduction a year ago, distributional approaches to reinforcement learning (distributional RL) have produced strong results relative to the standard approach which models expected values (expected RL). However, aside from convergence guarantees, there have been few theoretical results investigating the reasons behind the improvements distributional RL provides. In this paper we begin the investigation into this fundamental question by analyzing the differences in the tabular, linear approximation, and non-linear approximation settings. We prove that in many realizations of the ta","authors_text":"Clare Lyle, Marc G. Bellemare, Pablo Samuel Castro","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T20:20:27Z","title":"A Comparative Analysis of Expected and Distributional Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.11084","kind":"arxiv","version":2},"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":"sha256:2ba9789ee75d4004e44215d32a0fbad02a8feab0b359ef0f3261dbb558e236ae","target":"record","created_at":"2026-05-17T23:53:04Z","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":"5408797d38b4eecb53e048d6580a1858921db6746ed0774b60ae0addf55a0914","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-30T20:20:27Z","title_canon_sha256":"5e391539e2107da15f11daa5317149c6548ba48e8333366fb0d91c8f61b30ae0"},"schema_version":"1.0","source":{"id":"1901.11084","kind":"arxiv","version":2}},"canonical_sha256":"6c3f19aaf6278d575a1ecbc897d07786d5be1c0ccd644511dd20db322a2c4343","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c3f19aaf6278d575a1ecbc897d07786d5be1c0ccd644511dd20db322a2c4343","first_computed_at":"2026-05-17T23:53:04.147594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:04.147594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"34TPWVSrIYkE0oBBoU/kVRtzStiR7X8KlZIHqdSKAfu3mBej1ge4Ax6flxS7fYfrbOfhm3O91YTKz1yUYpJ4Cw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:04.148229Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.11084","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ba9789ee75d4004e44215d32a0fbad02a8feab0b359ef0f3261dbb558e236ae","sha256:600d58ffce505415fa7204221d4e5e0782f8e9e797ad8582911f49a2442a742b"],"state_sha256":"da0b4ed7aa67958dbc3da318bf6ab680029c11d264913cb68adca301086198ca"}