{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZLJ4E4JM3K65JWLHYINPNAKPI2","short_pith_number":"pith:ZLJ4E4JM","schema_version":"1.0","canonical_sha256":"cad3c2712cdabdd4d967c21af6814f46ba7e6c20ce0b6e6617f513cfcfd4ba8b","source":{"kind":"arxiv","id":"1808.08763","version":2},"attestation_state":"computed","paper":{"title":"On the convergence of optimistic policy iteration for stochastic shortest path problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Yuanlong Chen","submitted_at":"2018-08-27T09:51:03Z","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."},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1808.08763","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T09:51:03Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3709145376c0a2cf12e9f433c6b1ac76eb6d31aeade23daefb7fed418b7f3848","abstract_canon_sha256":"c0d8c051faf962542aeafd615c42b0de4dea93217a5693ab05c3de2cb0f51905"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:50.387000Z","signature_b64":"pB3a6m4KmMZQDqIQ+IubgLVHYRzczPBRLtYgycwh8DUeRURunn2oIRtsitIDit0m2Uu+jl13Q0KzpwCbuo75Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad3c2712cdabdd4d967c21af6814f46ba7e6c20ce0b6e6617f513cfcfd4ba8b","last_reissued_at":"2026-05-18T00:06:50.386207Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:50.386207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the convergence of optimistic policy iteration for stochastic shortest path problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Yuanlong Chen","submitted_at":"2018-08-27T09:51:03Z","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."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08763","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1808.08763","created_at":"2026-05-18T00:06:50.386341+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08763v2","created_at":"2026-05-18T00:06:50.386341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08763","created_at":"2026-05-18T00:06:50.386341+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLJ4E4JM3K65","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLJ4E4JM3K65JWLH","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLJ4E4JM","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLJ4E4JM3K65JWLHYINPNAKPI2","json":"https://pith.science/pith/ZLJ4E4JM3K65JWLHYINPNAKPI2.json","graph_json":"https://pith.science/api/pith-number/ZLJ4E4JM3K65JWLHYINPNAKPI2/graph.json","events_json":"https://pith.science/api/pith-number/ZLJ4E4JM3K65JWLHYINPNAKPI2/events.json","paper":"https://pith.science/paper/ZLJ4E4JM"},"agent_actions":{"view_html":"https://pith.science/pith/ZLJ4E4JM3K65JWLHYINPNAKPI2","download_json":"https://pith.science/pith/ZLJ4E4JM3K65JWLHYINPNAKPI2.json","view_paper":"https://pith.science/paper/ZLJ4E4JM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08763&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLJ4E4JM3K65JWLHYINPNAKPI2/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLJ4E4JM3K65JWLHYINPNAKPI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLJ4E4JM3K65JWLHYINPNAKPI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLJ4E4JM3K65JWLHYINPNAKPI2/action/storage_attestation","attest_author":"https://pith.science/pith/ZLJ4E4JM3K65JWLHYINPNAKPI2/action/author_attestation","sign_citation":"https://pith.science/pith/ZLJ4E4JM3K65JWLHYINPNAKPI2/action/citation_signature","submit_replication":"https://pith.science/pith/ZLJ4E4JM3K65JWLHYINPNAKPI2/action/replication_record"}},"created_at":"2026-05-18T00:06:50.386341+00:00","updated_at":"2026-05-18T00:06:50.386341+00:00"}