{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GZ75J4UMPR6VRAYDAYU5UXSAOX","short_pith_number":"pith:GZ75J4UM","schema_version":"1.0","canonical_sha256":"367fd4f28c7c7d5883030629da5e4075f173f8cd8de82cd7a55e30afdb983d77","source":{"kind":"arxiv","id":"2009.02476","version":4},"attestation_state":"computed","paper":{"title":"Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"Joseph L. Austerweil, Mark K. Ho, Xiaojin Zhu, Xuezhou Zhang, Yun-Shiuan Chuang, Yuzhe Ma","submitted_at":"2020-09-05T06:32:38Z","abstract_excerpt":"Successful teaching requires an assumption of how the learner learns - how the learner uses experiences from the world to update their internal states. We investigate what expectations people have about a learner when they teach them in an online manner using rewards and punishment. We focus on a common reinforcement learning method, Q-learning, and examine what assumptions people have using a behavioral experiment. To do so, we first establish a normative standard, by formulating the problem as a machine teaching optimization problem. To solve the machine teaching optimization problem, we use"},"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":"2009.02476","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-05T06:32:38Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"9cc2c060562af578b6827fb7377a7ea5a2ecbe2b9e83a793b4a151e000a21502","abstract_canon_sha256":"ec36733ebf8c2863c552174c2cec4d186129940ba980c159a4d10922e286b280"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:25:56.305095Z","signature_b64":"eRQvVlTAiMhmCeuyCpByJTaaP1EnlMe9fQwGgDH6H0C9hyDlCAIR+8h2JJNvGG85ir3CUp791332HJwjE+xlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"367fd4f28c7c7d5883030629da5e4075f173f8cd8de82cd7a55e30afdb983d77","last_reissued_at":"2026-07-05T06:25:56.304707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:25:56.304707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.LG","authors_text":"Joseph L. Austerweil, Mark K. Ho, Xiaojin Zhu, Xuezhou Zhang, Yun-Shiuan Chuang, Yuzhe Ma","submitted_at":"2020-09-05T06:32:38Z","abstract_excerpt":"Successful teaching requires an assumption of how the learner learns - how the learner uses experiences from the world to update their internal states. We investigate what expectations people have about a learner when they teach them in an online manner using rewards and punishment. We focus on a common reinforcement learning method, Q-learning, and examine what assumptions people have using a behavioral experiment. To do so, we first establish a normative standard, by formulating the problem as a machine teaching optimization problem. To solve the machine teaching optimization problem, we use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.02476","kind":"arxiv","version":4},"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/2009.02476/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":"2009.02476","created_at":"2026-07-05T06:25:56.304761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.02476v4","created_at":"2026-07-05T06:25:56.304761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.02476","created_at":"2026-07-05T06:25:56.304761+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZ75J4UMPR6V","created_at":"2026-07-05T06:25:56.304761+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZ75J4UMPR6VRAYD","created_at":"2026-07-05T06:25:56.304761+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZ75J4UM","created_at":"2026-07-05T06:25:56.304761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.11761","citing_title":"Mapping out the Space of Human Feedback for Reinforcement Learning: A Conceptual Framework","ref_index":43,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZ75J4UMPR6VRAYDAYU5UXSAOX","json":"https://pith.science/pith/GZ75J4UMPR6VRAYDAYU5UXSAOX.json","graph_json":"https://pith.science/api/pith-number/GZ75J4UMPR6VRAYDAYU5UXSAOX/graph.json","events_json":"https://pith.science/api/pith-number/GZ75J4UMPR6VRAYDAYU5UXSAOX/events.json","paper":"https://pith.science/paper/GZ75J4UM"},"agent_actions":{"view_html":"https://pith.science/pith/GZ75J4UMPR6VRAYDAYU5UXSAOX","download_json":"https://pith.science/pith/GZ75J4UMPR6VRAYDAYU5UXSAOX.json","view_paper":"https://pith.science/paper/GZ75J4UM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.02476&json=true","fetch_graph":"https://pith.science/api/pith-number/GZ75J4UMPR6VRAYDAYU5UXSAOX/graph.json","fetch_events":"https://pith.science/api/pith-number/GZ75J4UMPR6VRAYDAYU5UXSAOX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZ75J4UMPR6VRAYDAYU5UXSAOX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZ75J4UMPR6VRAYDAYU5UXSAOX/action/storage_attestation","attest_author":"https://pith.science/pith/GZ75J4UMPR6VRAYDAYU5UXSAOX/action/author_attestation","sign_citation":"https://pith.science/pith/GZ75J4UMPR6VRAYDAYU5UXSAOX/action/citation_signature","submit_replication":"https://pith.science/pith/GZ75J4UMPR6VRAYDAYU5UXSAOX/action/replication_record"}},"created_at":"2026-07-05T06:25:56.304761+00:00","updated_at":"2026-07-05T06:25:56.304761+00:00"}