{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZLJ4E4JM3K65JWLHYINPNAKPI2","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":"c0d8c051faf962542aeafd615c42b0de4dea93217a5693ab05c3de2cb0f51905","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T09:51:03Z","title_canon_sha256":"3709145376c0a2cf12e9f433c6b1ac76eb6d31aeade23daefb7fed418b7f3848"},"schema_version":"1.0","source":{"id":"1808.08763","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08763","created_at":"2026-05-18T00:06:50Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08763v2","created_at":"2026-05-18T00:06:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08763","created_at":"2026-05-18T00:06:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZLJ4E4JM3K65","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZLJ4E4JM3K65JWLH","created_at":"2026-05-18T12:33:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZLJ4E4JM","created_at":"2026-05-18T12:33:07Z"}],"graph_snapshots":[{"event_id":"sha256:025396e136e6cf66e46f3243b26415cdc622cd1d1d20e2df4a64dad3ef8aea10","target":"graph","created_at":"2026-05-18T00:06:50Z","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":"In this paper, we prove some convergence results of a special case of optimistic policy iteration algorithm for stochastic shortest path problem. We consider both Monte Carlo and $TD(\\lambda)$ methods for the policy evaluation step under the condition that the termination state will eventually be reached almost surely.","authors_text":"Yuanlong Chen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T09:51:03Z","title":"On the convergence of optimistic policy iteration for stochastic shortest path problem"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08763","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":"sha256:8b99272b8e7ba590f1488973e07369e832bf8e9784211194d96655903c64ea3c","target":"record","created_at":"2026-05-18T00:06:50Z","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":"c0d8c051faf962542aeafd615c42b0de4dea93217a5693ab05c3de2cb0f51905","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T09:51:03Z","title_canon_sha256":"3709145376c0a2cf12e9f433c6b1ac76eb6d31aeade23daefb7fed418b7f3848"},"schema_version":"1.0","source":{"id":"1808.08763","kind":"arxiv","version":2}},"canonical_sha256":"cad3c2712cdabdd4d967c21af6814f46ba7e6c20ce0b6e6617f513cfcfd4ba8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cad3c2712cdabdd4d967c21af6814f46ba7e6c20ce0b6e6617f513cfcfd4ba8b","first_computed_at":"2026-05-18T00:06:50.386207Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:50.386207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pB3a6m4KmMZQDqIQ+IubgLVHYRzczPBRLtYgycwh8DUeRURunn2oIRtsitIDit0m2Uu+jl13Q0KzpwCbuo75Dw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:50.387000Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.08763","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b99272b8e7ba590f1488973e07369e832bf8e9784211194d96655903c64ea3c","sha256:025396e136e6cf66e46f3243b26415cdc622cd1d1d20e2df4a64dad3ef8aea10"],"state_sha256":"f9b0d736a0cb76e12fd445a8bf188d24efe802c070aa3b326d028d86851316da"}