{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4ERWTNXZUIIJAWI2Y2XEH7RB5C","short_pith_number":"pith:4ERWTNXZ","canonical_record":{"source":{"id":"2002.03585","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T07:54:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5eb25c52e61956efaab219f779c358f303cabcb2946ac8e241323a94b5cb930e","abstract_canon_sha256":"cbab183693a7b7d65710f5be49fae2783d824a5148e1633c80044ba9f125d1cf"},"schema_version":"1.0"},"canonical_sha256":"e12369b6f9a21090591ac6ae43fe21e88996ac72cf745d3307845e14df741f61","source":{"kind":"arxiv","id":"2002.03585","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03585","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03585v2","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03585","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"4ERWTNXZUIIJ","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_16","alias_value":"4ERWTNXZUIIJAWI2","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_8","alias_value":"4ERWTNXZ","created_at":"2026-07-05T04:46:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4ERWTNXZUIIJAWI2Y2XEH7RB5C","target":"record","payload":{"canonical_record":{"source":{"id":"2002.03585","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T07:54:57Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5eb25c52e61956efaab219f779c358f303cabcb2946ac8e241323a94b5cb930e","abstract_canon_sha256":"cbab183693a7b7d65710f5be49fae2783d824a5148e1633c80044ba9f125d1cf"},"schema_version":"1.0"},"canonical_sha256":"e12369b6f9a21090591ac6ae43fe21e88996ac72cf745d3307845e14df741f61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:46:09.965433Z","signature_b64":"jjdUWlml9l8ayVv59yAlSRHdTBZg8ecdCHXt17RMSW2RaRJOvO/0nI9eSrD0Sd+Uk+SiOdy/+FXnj8gkQB6gDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e12369b6f9a21090591ac6ae43fe21e88996ac72cf745d3307845e14df741f61","last_reissued_at":"2026-07-05T04:46:09.965014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:46:09.965014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.03585","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SPyCsNz+FS6tJSO6KLF10xkkfc3lyuKX6gLRtJfZlyobjF3SEtyC0dFlN0/sWbTV60W7GG1WIKOMxnsoFiUDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:27:01.871155Z"},"content_sha256":"085ef50a1344b5b4c999f3188093813efda3763d7aa2b066295a43c0327a7fe5","schema_version":"1.0","event_id":"sha256:085ef50a1344b5b4c999f3188093813efda3763d7aa2b066295a43c0327a7fe5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4ERWTNXZUIIJAWI2Y2XEH7RB5C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Convergence of the Monte Carlo Exploring Starts Algorithm for Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Che Wang, Kai Shao, Keith Ross, Shuhan Yuan","submitted_at":"2020-02-10T07:54:57Z","abstract_excerpt":"A simple and natural algorithm for reinforcement learning (RL) is Monte Carlo Exploring Starts (MCES), where the Q-function is estimated by averaging the Monte Carlo returns, and the policy is improved by choosing actions that maximize the current estimate of the Q-function. Exploration is performed by \"exploring starts\", that is, each episode begins with a randomly chosen state and action, and then follows the current policy to the terminal state. In the classic book on RL by Sutton & Barto (2018), it is stated that establishing convergence for the MCES algorithm is one of the most important "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.03585","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/2002.03585/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":"2026-07-05T04:46:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wqg8WAaxDn1tyWIFBDMN6d71P1P8y6BZH9txPdWHVhhKso0bIDWgtmjxNVR06ycS3xr9E6kOwftaOUn6nc6TBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T10:27:01.871747Z"},"content_sha256":"9648a4eb743a6d76a5a210ce7e4b8278b589f9f014d9f3d30802871a71895608","schema_version":"1.0","event_id":"sha256:9648a4eb743a6d76a5a210ce7e4b8278b589f9f014d9f3d30802871a71895608"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4ERWTNXZUIIJAWI2Y2XEH7RB5C/bundle.json","state_url":"https://pith.science/pith/4ERWTNXZUIIJAWI2Y2XEH7RB5C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4ERWTNXZUIIJAWI2Y2XEH7RB5C/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":"2026-08-15T10:27:01Z","links":{"resolver":"https://pith.science/pith/4ERWTNXZUIIJAWI2Y2XEH7RB5C","bundle":"https://pith.science/pith/4ERWTNXZUIIJAWI2Y2XEH7RB5C/bundle.json","state":"https://pith.science/pith/4ERWTNXZUIIJAWI2Y2XEH7RB5C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4ERWTNXZUIIJAWI2Y2XEH7RB5C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4ERWTNXZUIIJAWI2Y2XEH7RB5C","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":"cbab183693a7b7d65710f5be49fae2783d824a5148e1633c80044ba9f125d1cf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T07:54:57Z","title_canon_sha256":"5eb25c52e61956efaab219f779c358f303cabcb2946ac8e241323a94b5cb930e"},"schema_version":"1.0","source":{"id":"2002.03585","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.03585","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"arxiv_version","alias_value":"2002.03585v2","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.03585","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_12","alias_value":"4ERWTNXZUIIJ","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_16","alias_value":"4ERWTNXZUIIJAWI2","created_at":"2026-07-05T04:46:09Z"},{"alias_kind":"pith_short_8","alias_value":"4ERWTNXZ","created_at":"2026-07-05T04:46:09Z"}],"graph_snapshots":[{"event_id":"sha256:9648a4eb743a6d76a5a210ce7e4b8278b589f9f014d9f3d30802871a71895608","target":"graph","created_at":"2026-07-05T04:46:09Z","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/2002.03585/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A simple and natural algorithm for reinforcement learning (RL) is Monte Carlo Exploring Starts (MCES), where the Q-function is estimated by averaging the Monte Carlo returns, and the policy is improved by choosing actions that maximize the current estimate of the Q-function. Exploration is performed by \"exploring starts\", that is, each episode begins with a randomly chosen state and action, and then follows the current policy to the terminal state. In the classic book on RL by Sutton & Barto (2018), it is stated that establishing convergence for the MCES algorithm is one of the most important ","authors_text":"Che Wang, Kai Shao, Keith Ross, Shuhan Yuan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T07:54:57Z","title":"On the Convergence 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":"2002.03585","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":"sha256:085ef50a1344b5b4c999f3188093813efda3763d7aa2b066295a43c0327a7fe5","target":"record","created_at":"2026-07-05T04:46:09Z","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":"cbab183693a7b7d65710f5be49fae2783d824a5148e1633c80044ba9f125d1cf","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-10T07:54:57Z","title_canon_sha256":"5eb25c52e61956efaab219f779c358f303cabcb2946ac8e241323a94b5cb930e"},"schema_version":"1.0","source":{"id":"2002.03585","kind":"arxiv","version":2}},"canonical_sha256":"e12369b6f9a21090591ac6ae43fe21e88996ac72cf745d3307845e14df741f61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e12369b6f9a21090591ac6ae43fe21e88996ac72cf745d3307845e14df741f61","first_computed_at":"2026-07-05T04:46:09.965014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:46:09.965014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jjdUWlml9l8ayVv59yAlSRHdTBZg8ecdCHXt17RMSW2RaRJOvO/0nI9eSrD0Sd+Uk+SiOdy/+FXnj8gkQB6gDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:46:09.965433Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.03585","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:085ef50a1344b5b4c999f3188093813efda3763d7aa2b066295a43c0327a7fe5","sha256:9648a4eb743a6d76a5a210ce7e4b8278b589f9f014d9f3d30802871a71895608"],"state_sha256":"ef73473d358a1973ae251d2b5281e2ab6752ed3e01527e516e966c271fa643d3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G539wrNrlJgWiIXQ2rufafuOW0HYSOnMtIHXfxd0RzsoOrnC4S8sIl6oEibdSQtq8EvrFmNNuIHDl4Y5ElXoBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T10:27:01.877729Z","bundle_sha256":"320eb1af55a0f3e3cb7aad862ea8f56c6700ce30f3704a56ef8a4aca64fdd404"}}