{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:YPNOPOV5ZNS4PHGCPMNM4SA2J5","short_pith_number":"pith:YPNOPOV5","schema_version":"1.0","canonical_sha256":"c3dae7babdcb65c79cc27b1ace481a4f536d7b0267dadad95db89e413c38380c","source":{"kind":"arxiv","id":"2212.12167","version":1},"attestation_state":"computed","paper":{"title":"Offline Reinforcement Learning for Human-Guided Human-Machine Interaction with Private Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Lan Wang, Zhaoran Wang, Zhengling Qi, Zhuoran Yang, Zuyue Fu","submitted_at":"2022-12-23T06:26:44Z","abstract_excerpt":"Motivated by the human-machine interaction such as training chatbots for improving customer satisfaction, we study human-guided human-machine interaction involving private information. We model this interaction as a two-player turn-based game, where one player (Alice, a human) guides the other player (Bob, a machine) towards a common goal. Specifically, we focus on offline reinforcement learning (RL) in this game, where the goal is to find a policy pair for Alice and Bob that maximizes their expected total rewards based on an offline dataset collected a priori. The offline setting presents two"},"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":"2212.12167","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-12-23T06:26:44Z","cross_cats_sorted":["cs.LG","stat.ME"],"title_canon_sha256":"af59c634973959d5b59e8c0b2c52bdfd013b771792b3b93fb1f345d8e42fd1cf","abstract_canon_sha256":"be34720e55def66e33fa7f8df1eb62fbf340dea40ea0878d9c447e3701f42169"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:27:52.583363Z","signature_b64":"BSWxzxTFw+LMLv/gTasgJqAIy2MWVcWkOKSVKSvhFKas/GbsmdjkBBKEwYEE9V77iYQEdl3NswXnRCLsaycGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3dae7babdcb65c79cc27b1ace481a4f536d7b0267dadad95db89e413c38380c","last_reissued_at":"2026-07-05T05:27:52.582966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:27:52.582966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Offline Reinforcement Learning for Human-Guided Human-Machine Interaction with Private Information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ME"],"primary_cat":"stat.ML","authors_text":"Lan Wang, Zhaoran Wang, Zhengling Qi, Zhuoran Yang, Zuyue Fu","submitted_at":"2022-12-23T06:26:44Z","abstract_excerpt":"Motivated by the human-machine interaction such as training chatbots for improving customer satisfaction, we study human-guided human-machine interaction involving private information. We model this interaction as a two-player turn-based game, where one player (Alice, a human) guides the other player (Bob, a machine) towards a common goal. Specifically, we focus on offline reinforcement learning (RL) in this game, where the goal is to find a policy pair for Alice and Bob that maximizes their expected total rewards based on an offline dataset collected a priori. The offline setting presents two"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.12167","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2212.12167/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2212.12167","created_at":"2026-07-05T05:27:52.583020+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.12167v1","created_at":"2026-07-05T05:27:52.583020+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.12167","created_at":"2026-07-05T05:27:52.583020+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPNOPOV5ZNS4","created_at":"2026-07-05T05:27:52.583020+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPNOPOV5ZNS4PHGC","created_at":"2026-07-05T05:27:52.583020+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPNOPOV5","created_at":"2026-07-05T05:27:52.583020+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/YPNOPOV5ZNS4PHGCPMNM4SA2J5","json":"https://pith.science/pith/YPNOPOV5ZNS4PHGCPMNM4SA2J5.json","graph_json":"https://pith.science/api/pith-number/YPNOPOV5ZNS4PHGCPMNM4SA2J5/graph.json","events_json":"https://pith.science/api/pith-number/YPNOPOV5ZNS4PHGCPMNM4SA2J5/events.json","paper":"https://pith.science/paper/YPNOPOV5"},"agent_actions":{"view_html":"https://pith.science/pith/YPNOPOV5ZNS4PHGCPMNM4SA2J5","download_json":"https://pith.science/pith/YPNOPOV5ZNS4PHGCPMNM4SA2J5.json","view_paper":"https://pith.science/paper/YPNOPOV5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.12167&json=true","fetch_graph":"https://pith.science/api/pith-number/YPNOPOV5ZNS4PHGCPMNM4SA2J5/graph.json","fetch_events":"https://pith.science/api/pith-number/YPNOPOV5ZNS4PHGCPMNM4SA2J5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPNOPOV5ZNS4PHGCPMNM4SA2J5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPNOPOV5ZNS4PHGCPMNM4SA2J5/action/storage_attestation","attest_author":"https://pith.science/pith/YPNOPOV5ZNS4PHGCPMNM4SA2J5/action/author_attestation","sign_citation":"https://pith.science/pith/YPNOPOV5ZNS4PHGCPMNM4SA2J5/action/citation_signature","submit_replication":"https://pith.science/pith/YPNOPOV5ZNS4PHGCPMNM4SA2J5/action/replication_record"}},"created_at":"2026-07-05T05:27:52.583020+00:00","updated_at":"2026-07-05T05:27:52.583020+00:00"}