{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FRYS3NVJCVYKHFRRDTPLXIGHSY","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":"55d16615d6c7486aff2b8e6ac466308166244134ddeb9065b0536cc05352d1d2","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-02T16:48:14Z","title_canon_sha256":"4430cbedd5b3479ebe3a8d3987c99ae2001cf3acdd7b606bf1a2bb3b2c1314c6"},"schema_version":"1.0","source":{"id":"2211.01266","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.01266","created_at":"2026-07-05T05:12:45Z"},{"alias_kind":"arxiv_version","alias_value":"2211.01266v1","created_at":"2026-07-05T05:12:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.01266","created_at":"2026-07-05T05:12:45Z"},{"alias_kind":"pith_short_12","alias_value":"FRYS3NVJCVYK","created_at":"2026-07-05T05:12:45Z"},{"alias_kind":"pith_short_16","alias_value":"FRYS3NVJCVYKHFRR","created_at":"2026-07-05T05:12:45Z"},{"alias_kind":"pith_short_8","alias_value":"FRYS3NVJ","created_at":"2026-07-05T05:12:45Z"}],"graph_snapshots":[{"event_id":"sha256:25ebf124d08d22d46bdb608327692aa7bbf526ee2918687754ce5ec0a31ebd18","target":"graph","created_at":"2026-07-05T05:12:45Z","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/2211.01266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL)-based control system has received considerable attention in recent decades. However, in many real-world problems, such as Batch Process Control, the environment is uncertain, which requires expensive interaction to acquire the state and reward values. In this paper, we present a cost-efficient framework, such that the RL model can evolve for itself in a Virtual Space using the predictive models with only historical data. The proposed framework enables a step-by-step RL model to predict the future state and select optimal actions for long-sight decisions. The main fo","authors_text":"BingZhang Hu, Haoran Duan, Noura Al Moubayed, Peng Zhang, Shizheng Wang, Yang Long, Yawen Huang, Yefeng Zheng","cross_cats":["cs.AI","cs.SY","eess.SY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-02T16:48:14Z","title":"Knowing the Past to Predict the Future: Reinforcement Virtual Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.01266","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":"sha256:734d6311404b95e16897b4a8268cc4c5fc8705c35d85429345e827994834ba37","target":"record","created_at":"2026-07-05T05:12:45Z","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":"55d16615d6c7486aff2b8e6ac466308166244134ddeb9065b0536cc05352d1d2","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-11-02T16:48:14Z","title_canon_sha256":"4430cbedd5b3479ebe3a8d3987c99ae2001cf3acdd7b606bf1a2bb3b2c1314c6"},"schema_version":"1.0","source":{"id":"2211.01266","kind":"arxiv","version":1}},"canonical_sha256":"2c712db6a91570a396311cdebba0c7962f09641f2c37c3edef33b5467070bcde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2c712db6a91570a396311cdebba0c7962f09641f2c37c3edef33b5467070bcde","first_computed_at":"2026-07-05T05:12:45.478270Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:12:45.478270Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qBC1Pi6LdCrPhmJbQYD7n9Fja9UIn35vE4SpwH13lTRCoDhdVNsDXgYU9yzMoEmECv4ah3DVtmm46XT2HVt/BA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:12:45.478754Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.01266","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:734d6311404b95e16897b4a8268cc4c5fc8705c35d85429345e827994834ba37","sha256:25ebf124d08d22d46bdb608327692aa7bbf526ee2918687754ce5ec0a31ebd18"],"state_sha256":"c45a23d5e058a197725ee00840942294e210627f2968472e3cc66e7dfe082f20"}