{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:NVPVVRC2RCP2VGFGKEKLX5Q5N3","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":"a151b1919ad82c80b9fa69348e841885d718ba235b841a53d12fb36a90fcaca0","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-27T05:13:29Z","title_canon_sha256":"30c9faccd83d25eecdfad805605cd5d111a9f41ee53e4e1c7e1ddf9244be9cba"},"schema_version":"1.0","source":{"id":"2003.12239","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12239","created_at":"2026-07-05T00:50:56Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12239v1","created_at":"2026-07-05T00:50:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12239","created_at":"2026-07-05T00:50:56Z"},{"alias_kind":"pith_short_12","alias_value":"NVPVVRC2RCP2","created_at":"2026-07-05T00:50:56Z"},{"alias_kind":"pith_short_16","alias_value":"NVPVVRC2RCP2VGFG","created_at":"2026-07-05T00:50:56Z"},{"alias_kind":"pith_short_8","alias_value":"NVPVVRC2","created_at":"2026-07-05T00:50:56Z"}],"graph_snapshots":[{"event_id":"sha256:f60e4883388b224a88cea9d0c67b0f231be73f29e1bb72b8756454dff37ad952","target":"graph","created_at":"2026-07-05T00:50:56Z","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/2003.12239/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a distributional approach to theoretical analyses of reinforcement learning algorithms for constant step-sizes. We demonstrate its effectiveness by presenting simple and unified proofs of convergence for a variety of commonly-used methods. We show that value-based methods such as TD($\\lambda$) and $Q$-Learning have update rules which are contractive in the space of distributions of functions, thus establishing their exponentially fast convergence to a stationary distribution. We demonstrate that the stationary distribution obtained by any algorithm whose target is an expected Bellma","authors_text":"Doina Precup, Marc G. Bellemare, Philip Amortila, Prakash Panangaden","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-27T05:13:29Z","title":"A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12239","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:e3c44a14698a144d2aa7cc2990f99c68ab5a32aa60869b5cb69eb7266791428f","target":"record","created_at":"2026-07-05T00:50:56Z","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":"a151b1919ad82c80b9fa69348e841885d718ba235b841a53d12fb36a90fcaca0","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-27T05:13:29Z","title_canon_sha256":"30c9faccd83d25eecdfad805605cd5d111a9f41ee53e4e1c7e1ddf9244be9cba"},"schema_version":"1.0","source":{"id":"2003.12239","kind":"arxiv","version":1}},"canonical_sha256":"6d5f5ac45a889faa98a65114bbf61d6ed8180ed2e3df633e249104895561603c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d5f5ac45a889faa98a65114bbf61d6ed8180ed2e3df633e249104895561603c","first_computed_at":"2026-07-05T00:50:56.615225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:50:56.615225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Z/G1TtzrVOYRuOHkZ6PLJU9ZqCdy8kb/f4zPygcWJnPiujE09Lc2OyaCOiGVCzVfg4ez7kAHg7xm+QLz+cF3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:50:56.615766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.12239","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e3c44a14698a144d2aa7cc2990f99c68ab5a32aa60869b5cb69eb7266791428f","sha256:f60e4883388b224a88cea9d0c67b0f231be73f29e1bb72b8756454dff37ad952"],"state_sha256":"8932efa75655bd62f7554579a3cd7250eb232228b765196023a4704a9ac0fbfa"}