{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:XVBIJG6RCIEHDZFKBVPQOTBYP2","short_pith_number":"pith:XVBIJG6R","schema_version":"1.0","canonical_sha256":"bd42849bd1120871e4aa0d5f074c387eaee08be5be53e53e2e8b6a0cf5c95275","source":{"kind":"arxiv","id":"1301.5488","version":1},"attestation_state":"computed","paper":{"title":"Multi-class Generalized Binary Search for Active 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":"Francisco Melo, Manuel Lopes","submitted_at":"2013-01-23T12:54:09Z","abstract_excerpt":"This paper addresses the problem of learning a task from demonstration. We adopt the framework of inverse reinforcement learning, where tasks are represented in the form of a reward function. Our contribution is a novel active learning algorithm that enables the learning agent to query the expert for more informative demonstrations, thus leading to more sample-efficient learning. For this novel algorithm (Generalized Binary Search for Inverse Reinforcement Learning, or GBS-IRL), we provide a theoretical bound on sample complexity and illustrate its applicability on several different tasks. To "},"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":"1301.5488","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-01-23T12:54:09Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"3acc572b3a046fb3820f6c9f8406bb895d0bd07a0dfdaa4a3d2218e902ada20a","abstract_canon_sha256":"b6dc6ba63e6fa36c1d013f55c942c32a8d450017bc82b080e2a81affdc9ff20d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:35:39.649479Z","signature_b64":"V3yIw1AX5ObpNEnB59tgJ7kGeaR6gtfQ/X+y8uqyCXsehGsH3OlJPVRXa6YG9GUeUC1oR67MqaPhsfSLiqdsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd42849bd1120871e4aa0d5f074c387eaee08be5be53e53e2e8b6a0cf5c95275","last_reissued_at":"2026-05-18T03:35:39.648713Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:35:39.648713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-class Generalized Binary Search for Active 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":"Francisco Melo, Manuel Lopes","submitted_at":"2013-01-23T12:54:09Z","abstract_excerpt":"This paper addresses the problem of learning a task from demonstration. We adopt the framework of inverse reinforcement learning, where tasks are represented in the form of a reward function. Our contribution is a novel active learning algorithm that enables the learning agent to query the expert for more informative demonstrations, thus leading to more sample-efficient learning. For this novel algorithm (Generalized Binary Search for Inverse Reinforcement Learning, or GBS-IRL), we provide a theoretical bound on sample complexity and illustrate its applicability on several different tasks. To "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1301.5488","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":""},"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":"1301.5488","created_at":"2026-05-18T03:35:39.648839+00:00"},{"alias_kind":"arxiv_version","alias_value":"1301.5488v1","created_at":"2026-05-18T03:35:39.648839+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1301.5488","created_at":"2026-05-18T03:35:39.648839+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVBIJG6RCIEH","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVBIJG6RCIEHDZFK","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVBIJG6R","created_at":"2026-05-18T12:28:06.772260+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/XVBIJG6RCIEHDZFKBVPQOTBYP2","json":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2.json","graph_json":"https://pith.science/api/pith-number/XVBIJG6RCIEHDZFKBVPQOTBYP2/graph.json","events_json":"https://pith.science/api/pith-number/XVBIJG6RCIEHDZFKBVPQOTBYP2/events.json","paper":"https://pith.science/paper/XVBIJG6R"},"agent_actions":{"view_html":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2","download_json":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2.json","view_paper":"https://pith.science/paper/XVBIJG6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1301.5488&json=true","fetch_graph":"https://pith.science/api/pith-number/XVBIJG6RCIEHDZFKBVPQOTBYP2/graph.json","fetch_events":"https://pith.science/api/pith-number/XVBIJG6RCIEHDZFKBVPQOTBYP2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/action/storage_attestation","attest_author":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/action/author_attestation","sign_citation":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/action/citation_signature","submit_replication":"https://pith.science/pith/XVBIJG6RCIEHDZFKBVPQOTBYP2/action/replication_record"}},"created_at":"2026-05-18T03:35:39.648839+00:00","updated_at":"2026-05-18T03:35:39.648839+00:00"}