{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:OJ45KLNOUIZIWOOYEBDFIE4CDE","short_pith_number":"pith:OJ45KLNO","schema_version":"1.0","canonical_sha256":"7279d52daea2328b39d82046541382190581bdc1117cc0f13ce3c6dfebb036fc","source":{"kind":"arxiv","id":"2006.09324","version":2},"attestation_state":"computed","paper":{"title":"The Sample Complexity of Teaching-by-Reinforcement on Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adish Singla, Shubham Kumar Bharti, Xiaojin Zhu, Xuezhou Zhang, Yuzhe Ma","submitted_at":"2020-06-16T17:06:04Z","abstract_excerpt":"We study the sample complexity of teaching, termed as \"teaching dimension\" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the student through rewards. This is distinct from the teaching-by-demonstration paradigm motivated by robotics applications, where the teacher teaches by providing demonstrations of state/action trajectories. The teaching-by-reinforcement paradigm applies to a wider range of real-world settings where a demonstration is inconvenient, but has not been studied systematically. In this paper, we focus on a specific family of reinf"},"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":"2006.09324","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-16T17:06:04Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"521f837cdead54b8c6fb784e1be13dc5614befe569432d485b0b159130679427","abstract_canon_sha256":"398edb1b371d95477fe720275d69f4e602cac1b753eb697d854b2f5e13fdf5b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:55.383018Z","signature_b64":"NixznmjIm1qzkne6ssIzjCjkt9nqkeiIdhdKHw/ZVH3lxfXBtsnRZH5H7zclsSvDLHJR9WXquUQaU62C7XBbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7279d52daea2328b39d82046541382190581bdc1117cc0f13ce3c6dfebb036fc","last_reissued_at":"2026-07-05T02:20:55.382507Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:55.382507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Sample Complexity of Teaching-by-Reinforcement on Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adish Singla, Shubham Kumar Bharti, Xiaojin Zhu, Xuezhou Zhang, Yuzhe Ma","submitted_at":"2020-06-16T17:06:04Z","abstract_excerpt":"We study the sample complexity of teaching, termed as \"teaching dimension\" (TDim) in the literature, for the teaching-by-reinforcement paradigm, where the teacher guides the student through rewards. This is distinct from the teaching-by-demonstration paradigm motivated by robotics applications, where the teacher teaches by providing demonstrations of state/action trajectories. The teaching-by-reinforcement paradigm applies to a wider range of real-world settings where a demonstration is inconvenient, but has not been studied systematically. In this paper, we focus on a specific family of reinf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.09324","kind":"arxiv","version":2},"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/2006.09324/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":"2006.09324","created_at":"2026-07-05T02:20:55.382577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.09324v2","created_at":"2026-07-05T02:20:55.382577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.09324","created_at":"2026-07-05T02:20:55.382577+00:00"},{"alias_kind":"pith_short_12","alias_value":"OJ45KLNOUIZI","created_at":"2026-07-05T02:20:55.382577+00:00"},{"alias_kind":"pith_short_16","alias_value":"OJ45KLNOUIZIWOOY","created_at":"2026-07-05T02:20:55.382577+00:00"},{"alias_kind":"pith_short_8","alias_value":"OJ45KLNO","created_at":"2026-07-05T02:20:55.382577+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/OJ45KLNOUIZIWOOYEBDFIE4CDE","json":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE.json","graph_json":"https://pith.science/api/pith-number/OJ45KLNOUIZIWOOYEBDFIE4CDE/graph.json","events_json":"https://pith.science/api/pith-number/OJ45KLNOUIZIWOOYEBDFIE4CDE/events.json","paper":"https://pith.science/paper/OJ45KLNO"},"agent_actions":{"view_html":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE","download_json":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE.json","view_paper":"https://pith.science/paper/OJ45KLNO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.09324&json=true","fetch_graph":"https://pith.science/api/pith-number/OJ45KLNOUIZIWOOYEBDFIE4CDE/graph.json","fetch_events":"https://pith.science/api/pith-number/OJ45KLNOUIZIWOOYEBDFIE4CDE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/action/storage_attestation","attest_author":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/action/author_attestation","sign_citation":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/action/citation_signature","submit_replication":"https://pith.science/pith/OJ45KLNOUIZIWOOYEBDFIE4CDE/action/replication_record"}},"created_at":"2026-07-05T02:20:55.382577+00:00","updated_at":"2026-07-05T02:20:55.382577+00:00"}