{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YP2GWEONAJOZAUEVR5A7EAGA55","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":"f7e0a236bc5ea99ad44c343f6bce7139009d21b2d87a7cc823bd2f6eba8fd502","cross_cats_sorted":["cs.AI","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T22:03:58Z","title_canon_sha256":"b2ea5f7578410c8d6104be7c23b4635fea014eb99b71a83b56f1409091f568d4"},"schema_version":"1.0","source":{"id":"1810.12429","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.12429","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"arxiv_version","alias_value":"1810.12429v1","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.12429","created_at":"2026-05-18T00:02:02Z"},{"alias_kind":"pith_short_12","alias_value":"YP2GWEONAJOZ","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YP2GWEONAJOZAUEV","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YP2GWEON","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:22ecbd2f10df35e0d20d7445a6a077309a91a80efadbdd32ed3fc635424a4e6b","target":"graph","created_at":"2026-05-18T00:02:02Z","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":"We consider the off-policy estimation problem of estimating the expected reward of a target policy using samples collected by a different behavior policy. Importance sampling (IS) has been a key technique to derive (nearly) unbiased estimators, but is known to suffer from an excessively high variance in long-horizon problems. In the extreme case of in infinite-horizon problems, the variance of an IS-based estimator may even be unbounded. In this paper, we propose a new off-policy estimation method that applies IS directly on the stationary state-visitation distributions to avoid the exploding ","authors_text":"Dengyong Zhou, Lihong Li, Qiang Liu, Ziyang Tang","cross_cats":["cs.AI","cs.SY","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T22:03:58Z","title":"Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.12429","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:e50f8d6ba95d1c1ac67021bd11eb8305d38229a5ff466f8d32b18a6283afc057","target":"record","created_at":"2026-05-18T00:02:02Z","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":"f7e0a236bc5ea99ad44c343f6bce7139009d21b2d87a7cc823bd2f6eba8fd502","cross_cats_sorted":["cs.AI","cs.SY","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-29T22:03:58Z","title_canon_sha256":"b2ea5f7578410c8d6104be7c23b4635fea014eb99b71a83b56f1409091f568d4"},"schema_version":"1.0","source":{"id":"1810.12429","kind":"arxiv","version":1}},"canonical_sha256":"c3f46b11cd025d9050958f41f200c0ef74d2a8e7f4dc3bf4dc615afb51d611be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3f46b11cd025d9050958f41f200c0ef74d2a8e7f4dc3bf4dc615afb51d611be","first_computed_at":"2026-05-18T00:02:02.688608Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:02.688608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vwv/b2u4qMJMa81QcjP6kUime3DO0pOUoXBvK582SIT95smASOnRx0JR3QgQM5cbvyAOII09BBEQX0NRZR2qBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:02.689134Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.12429","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e50f8d6ba95d1c1ac67021bd11eb8305d38229a5ff466f8d32b18a6283afc057","sha256:22ecbd2f10df35e0d20d7445a6a077309a91a80efadbdd32ed3fc635424a4e6b"],"state_sha256":"c6d1e719e0fe416d9c6b5b3c0282eb2b45f8d4ee8960d0ce254d8e636960ba83"}