{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:5A4EZ44FRM4ASYMSZ3RHX2LT7A","short_pith_number":"pith:5A4EZ44F","schema_version":"1.0","canonical_sha256":"e8384cf3858b38096192cee27be973f828a6e2c0e10077215847fae238e39dce","source":{"kind":"arxiv","id":"1905.11867","version":3},"attestation_state":"computed","paper":{"title":"Interactive Teaching Algorithms for Inverse Reinforcement 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, Parameswaran Kamalaruban, Rati Devidze, Volkan Cevher","submitted_at":"2019-05-28T15:03:14Z","abstract_excerpt":"We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of demonstrations to an IRL learner to speed up the learning process? We present an interactive teaching framework where a teacher adaptively chooses the next demonstration based on learner's current policy. In particular, we design teaching algorithms for two concrete settings: an omniscient setting where a teacher has full knowledge about the learner"},"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":"1905.11867","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T15:03:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"15696678b98ae01eaf8116a712a260aa15b405b541ccf285290a8191f0a38f1f","abstract_canon_sha256":"a10ea9a5767a42a60a984901e5a9a12d4ada424246a4c0eb34454a15778f0d29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:02.082638Z","signature_b64":"B2B5qwU4mvOT3yBsZyYP1Knqg3K5RssfA9sPCWSh3AYqRVZ8yg5iF2Jo/ngDjYS+2wioD8PM4sMQlIBF+JS6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8384cf3858b38096192cee27be973f828a6e2c0e10077215847fae238e39dce","last_reissued_at":"2026-05-17T23:44:02.082131Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:02.082131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interactive Teaching Algorithms for Inverse Reinforcement 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, Parameswaran Kamalaruban, Rati Devidze, Volkan Cevher","submitted_at":"2019-05-28T15:03:14Z","abstract_excerpt":"We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of demonstrations to an IRL learner to speed up the learning process? We present an interactive teaching framework where a teacher adaptively chooses the next demonstration based on learner's current policy. In particular, we design teaching algorithms for two concrete settings: an omniscient setting where a teacher has full knowledge about the learner"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11867","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1905.11867","created_at":"2026-05-17T23:44:02.082213+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.11867v3","created_at":"2026-05-17T23:44:02.082213+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11867","created_at":"2026-05-17T23:44:02.082213+00:00"},{"alias_kind":"pith_short_12","alias_value":"5A4EZ44FRM4A","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"5A4EZ44FRM4ASYMS","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"5A4EZ44F","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08131","citing_title":"Interactive Inverse Reinforcement Learning of Interaction Scenarios via Bi-level Optimization","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A","json":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A.json","graph_json":"https://pith.science/api/pith-number/5A4EZ44FRM4ASYMSZ3RHX2LT7A/graph.json","events_json":"https://pith.science/api/pith-number/5A4EZ44FRM4ASYMSZ3RHX2LT7A/events.json","paper":"https://pith.science/paper/5A4EZ44F"},"agent_actions":{"view_html":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A","download_json":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A.json","view_paper":"https://pith.science/paper/5A4EZ44F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.11867&json=true","fetch_graph":"https://pith.science/api/pith-number/5A4EZ44FRM4ASYMSZ3RHX2LT7A/graph.json","fetch_events":"https://pith.science/api/pith-number/5A4EZ44FRM4ASYMSZ3RHX2LT7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/action/storage_attestation","attest_author":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/action/author_attestation","sign_citation":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/action/citation_signature","submit_replication":"https://pith.science/pith/5A4EZ44FRM4ASYMSZ3RHX2LT7A/action/replication_record"}},"created_at":"2026-05-17T23:44:02.082213+00:00","updated_at":"2026-05-17T23:44:02.082213+00:00"}