{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VHFO73CG4R72GIXTO3LDCGYEUM","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":"cc39c078c53c11019dcfc98653e922aeae148d01009984c1777271d91c7e4d85","cross_cats_sorted":["cs.LG","econ.EM","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-01-30T18:29:35Z","title_canon_sha256":"ae8a68f6add6e0fab715133a7a54cc5f79a1fc5d46534a59e4a9d1975217f101"},"schema_version":"1.0","source":{"id":"2301.13152","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13152","created_at":"2026-07-05T08:36:41Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13152v5","created_at":"2026-07-05T08:36:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13152","created_at":"2026-07-05T08:36:41Z"},{"alias_kind":"pith_short_12","alias_value":"VHFO73CG4R72","created_at":"2026-07-05T08:36:41Z"},{"alias_kind":"pith_short_16","alias_value":"VHFO73CG4R72GIXT","created_at":"2026-07-05T08:36:41Z"},{"alias_kind":"pith_short_8","alias_value":"VHFO73CG","created_at":"2026-07-05T08:36:41Z"}],"graph_snapshots":[{"event_id":"sha256:9c7abeae8e8a99db8f579321ae48deb11d5b69b631c6ed53223905e8415ab56b","target":"graph","created_at":"2026-07-05T08:36:41Z","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/2301.13152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Batch reinforcement learning (RL) aims at leveraging pre-collected data to find an optimal policy that maximizes the expected total rewards in a dynamic environment. The existing methods require absolutely continuous assumption (e.g., there do not exist non-overlapping regions) on the distribution induced by target policies with respect to the data distribution over either the state or action or both. We propose a new batch RL algorithm that allows for singularity for both state and action spaces (e.g., existence of non-overlapping regions between offline data distribution and the distribution","authors_text":"Runzhe Wan, Xiaohong Chen, Zhengling Qi","cross_cats":["cs.LG","econ.EM","stat.ME"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-01-30T18:29:35Z","title":"STEEL: Singularity-aware Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13152","kind":"arxiv","version":5},"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:a1cf4151d30b2f24d870fd02c1f1ba0db6faeb70b7d1384fd63aaa59e137e7c9","target":"record","created_at":"2026-07-05T08:36:41Z","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":"cc39c078c53c11019dcfc98653e922aeae148d01009984c1777271d91c7e4d85","cross_cats_sorted":["cs.LG","econ.EM","stat.ME"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-01-30T18:29:35Z","title_canon_sha256":"ae8a68f6add6e0fab715133a7a54cc5f79a1fc5d46534a59e4a9d1975217f101"},"schema_version":"1.0","source":{"id":"2301.13152","kind":"arxiv","version":5}},"canonical_sha256":"a9caefec46e47fa322f376d6311b04a319669d4c2e3c2f86a481f823df76770c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a9caefec46e47fa322f376d6311b04a319669d4c2e3c2f86a481f823df76770c","first_computed_at":"2026-07-05T08:36:41.818543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:41.818543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m9COmnLlwLH0s2wpHF7fzAe/yA1elNIqgNO0Sg5F6gP1fuWjNX2S5xteVkNLaMvukVLdhThFyeOeio9hTVzGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:41.819082Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13152","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1cf4151d30b2f24d870fd02c1f1ba0db6faeb70b7d1384fd63aaa59e137e7c9","sha256:9c7abeae8e8a99db8f579321ae48deb11d5b69b631c6ed53223905e8415ab56b"],"state_sha256":"63d12fca390fb79e09621d6dd75c1627133872b363c28868f814be7583824753"}