{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X7BDSFEHEE35HOW5JV6ROQAFB4","short_pith_number":"pith:X7BDSFEH","canonical_record":{"source":{"id":"2410.02994","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T21:11:29Z","cross_cats_sorted":[],"title_canon_sha256":"196df334006997376ba17208f84a3e8b353375d8705f634958c82374c71f83c2","abstract_canon_sha256":"8a9032d942fa988814c3010a8cca72f6b31f7b58f0836e5a5b74ddb1e75f7632"},"schema_version":"1.0"},"canonical_sha256":"bfc23914872137d3badd4d7d1740050f1861484f91b812bf03fb61422cb31b9f","source":{"kind":"arxiv","id":"2410.02994","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02994","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02994v1","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02994","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"X7BDSFEHEE35","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"X7BDSFEHEE35HOW5","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"X7BDSFEH","created_at":"2026-07-05T09:15:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X7BDSFEHEE35HOW5JV6ROQAFB4","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02994","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T21:11:29Z","cross_cats_sorted":[],"title_canon_sha256":"196df334006997376ba17208f84a3e8b353375d8705f634958c82374c71f83c2","abstract_canon_sha256":"8a9032d942fa988814c3010a8cca72f6b31f7b58f0836e5a5b74ddb1e75f7632"},"schema_version":"1.0"},"canonical_sha256":"bfc23914872137d3badd4d7d1740050f1861484f91b812bf03fb61422cb31b9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:42.725492Z","signature_b64":"wz3gSS8BPbpcnUy4KpcJvwv1Eug4R6rhmH73PN0XdHdiweCdystXYYSeY4W7BsVuqMJpdfYURDDat0x9mFmwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfc23914872137d3badd4d7d1740050f1861484f91b812bf03fb61422cb31b9f","last_reissued_at":"2026-07-05T09:15:42.724953Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:42.724953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02994","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":"2026-07-05T09:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EUD4cnXNW53iLG3M4wsN2az5itObbm+IucICSJEIExO+VDtt4HqiaAFS+WcdhZ7rSW8p8fB+lPZ9brA3MbVMBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:44:51.348614Z"},"content_sha256":"4f8f689ee7a547d508877fe9d574e5b4e4fc221f232eca3821e8d08c5914e0dd","schema_version":"1.0","event_id":"sha256:4f8f689ee7a547d508877fe9d574e5b4e4fc221f232eca3821e8d08c5914e0dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X7BDSFEHEE35HOW5JV6ROQAFB4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Finite-Sample Analysis of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Keith Ross, Pierre Youssef, Suei-Wen Chen","submitted_at":"2024-10-03T21:11:29Z","abstract_excerpt":"Monte Carlo Exploring Starts (MCES), which aims to learn the optimal policy using only sample returns, is a simple and natural algorithm in reinforcement learning which has been shown to converge under various conditions. However, the convergence rate analysis for MCES-style algorithms in the form of sample complexity has received very little attention. In this paper we develop a finite sample bound for a modified MCES algorithm which solves the stochastic shortest path problem. To this end, we prove a novel result on the convergence rate of the policy iteration algorithm. This result implies "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02994","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/2410.02994/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":"2026-07-05T09:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q6unuYhaZzYWGmlIDUjrkZ2ecSp+MIZm/s1cFtF/v/C5AIlX/9dUMv3IIAIyGiQLwR1LFgcO+ubUe6wiKItvBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:44:51.349407Z"},"content_sha256":"ae2c9eaae202e64a15a2b5f8922a8ed56a56d286e7baab975efb8b34a722750d","schema_version":"1.0","event_id":"sha256:ae2c9eaae202e64a15a2b5f8922a8ed56a56d286e7baab975efb8b34a722750d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X7BDSFEHEE35HOW5JV6ROQAFB4/bundle.json","state_url":"https://pith.science/pith/X7BDSFEHEE35HOW5JV6ROQAFB4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X7BDSFEHEE35HOW5JV6ROQAFB4/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":"2026-08-07T23:44:51Z","links":{"resolver":"https://pith.science/pith/X7BDSFEHEE35HOW5JV6ROQAFB4","bundle":"https://pith.science/pith/X7BDSFEHEE35HOW5JV6ROQAFB4/bundle.json","state":"https://pith.science/pith/X7BDSFEHEE35HOW5JV6ROQAFB4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X7BDSFEHEE35HOW5JV6ROQAFB4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X7BDSFEHEE35HOW5JV6ROQAFB4","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":"8a9032d942fa988814c3010a8cca72f6b31f7b58f0836e5a5b74ddb1e75f7632","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T21:11:29Z","title_canon_sha256":"196df334006997376ba17208f84a3e8b353375d8705f634958c82374c71f83c2"},"schema_version":"1.0","source":{"id":"2410.02994","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02994","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02994v1","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02994","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"X7BDSFEHEE35","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"X7BDSFEHEE35HOW5","created_at":"2026-07-05T09:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"X7BDSFEH","created_at":"2026-07-05T09:15:42Z"}],"graph_snapshots":[{"event_id":"sha256:ae2c9eaae202e64a15a2b5f8922a8ed56a56d286e7baab975efb8b34a722750d","target":"graph","created_at":"2026-07-05T09:15:42Z","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/2410.02994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Monte Carlo Exploring Starts (MCES), which aims to learn the optimal policy using only sample returns, is a simple and natural algorithm in reinforcement learning which has been shown to converge under various conditions. However, the convergence rate analysis for MCES-style algorithms in the form of sample complexity has received very little attention. In this paper we develop a finite sample bound for a modified MCES algorithm which solves the stochastic shortest path problem. To this end, we prove a novel result on the convergence rate of the policy iteration algorithm. This result implies ","authors_text":"Keith Ross, Pierre Youssef, Suei-Wen Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T21:11:29Z","title":"Finite-Sample Analysis of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02994","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":"sha256:4f8f689ee7a547d508877fe9d574e5b4e4fc221f232eca3821e8d08c5914e0dd","target":"record","created_at":"2026-07-05T09:15:42Z","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":"8a9032d942fa988814c3010a8cca72f6b31f7b58f0836e5a5b74ddb1e75f7632","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T21:11:29Z","title_canon_sha256":"196df334006997376ba17208f84a3e8b353375d8705f634958c82374c71f83c2"},"schema_version":"1.0","source":{"id":"2410.02994","kind":"arxiv","version":1}},"canonical_sha256":"bfc23914872137d3badd4d7d1740050f1861484f91b812bf03fb61422cb31b9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfc23914872137d3badd4d7d1740050f1861484f91b812bf03fb61422cb31b9f","first_computed_at":"2026-07-05T09:15:42.724953Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:42.724953Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wz3gSS8BPbpcnUy4KpcJvwv1Eug4R6rhmH73PN0XdHdiweCdystXYYSeY4W7BsVuqMJpdfYURDDat0x9mFmwBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:42.725492Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02994","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4f8f689ee7a547d508877fe9d574e5b4e4fc221f232eca3821e8d08c5914e0dd","sha256:ae2c9eaae202e64a15a2b5f8922a8ed56a56d286e7baab975efb8b34a722750d"],"state_sha256":"be69fbd2eeba936f8e85e73a3e2103bdf65a7c016dae5f524050c8a0eccb7187"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hx5yKqw3ZmRIJeEx9HOC7WGBpgT4hMRrmJJrNY9pvnwDwtLT8v7myE7L+lVSDSaB17Q8xOk0tj+cpVz6yZ84DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:44:51.355279Z","bundle_sha256":"b69340a4a2016a85a1c105959a8524ff07dd69baebe8dfc5b8cec4543d87ac85"}}