{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZAVCFJOTZLUMYB4O7BMCXCTIRC","short_pith_number":"pith:ZAVCFJOT","schema_version":"1.0","canonical_sha256":"c82a22a5d3cae8cc078ef8582b8a68889cf4eb0a04c3ea1486aa2fb74163b055","source":{"kind":"arxiv","id":"1906.08928","version":1},"attestation_state":"computed","paper":{"title":"Learning Reward Functions by Integrating Human Demonstrations and Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Dorsa Sadigh, Gleb Shevchuk, Malayandi Palan, Nicholas C. Landolfi","submitted_at":"2019-06-21T03:00:36Z","abstract_excerpt":"Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses expert demonstrations, and preference-based learning, which iteratively queries the user for her preferences between trajectories. In robotics however, IRL often struggles because it is difficult to get high-quality demonstrations; conversely, preference-based learning is very inefficient since it attempts to learn a continuous, high-dimensional function from binary feedback. We propose a new framework for reward lea"},"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":"1906.08928","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2019-06-21T03:00:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2bb2f312496df5de7628d2aa467f338b31a090c5a73c84cbec939255c13d5fa5","abstract_canon_sha256":"ba8b33de2e53a4ad64656442819fef29e22095e4725565ab7b4413c46ecd3cce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:47.377351Z","signature_b64":"XUteongKia8n3NJ3BEY6K28P8GBBI2QTRvVeWETF/zEkQMfYg04xvM2pF1ZBmuUQJ9hvvRWKZDhX+ZXpuQ9hDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c82a22a5d3cae8cc078ef8582b8a68889cf4eb0a04c3ea1486aa2fb74163b055","last_reissued_at":"2026-05-17T23:42:47.376672Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:47.376672Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Reward Functions by Integrating Human Demonstrations and Preferences","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Dorsa Sadigh, Gleb Shevchuk, Malayandi Palan, Nicholas C. Landolfi","submitted_at":"2019-06-21T03:00:36Z","abstract_excerpt":"Our goal is to accurately and efficiently learn reward functions for autonomous robots. Current approaches to this problem include inverse reinforcement learning (IRL), which uses expert demonstrations, and preference-based learning, which iteratively queries the user for her preferences between trajectories. In robotics however, IRL often struggles because it is difficult to get high-quality demonstrations; conversely, preference-based learning is very inefficient since it attempts to learn a continuous, high-dimensional function from binary feedback. We propose a new framework for reward lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.08928","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":"1906.08928","created_at":"2026-05-17T23:42:47.376788+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.08928v1","created_at":"2026-05-17T23:42:47.376788+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.08928","created_at":"2026-05-17T23:42:47.376788+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAVCFJOTZLUM","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAVCFJOTZLUMYB4O","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAVCFJOT","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.02349","citing_title":"OPRIDE: Offline Preference-based Reinforcement Learning via In-Dataset Exploration","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZAVCFJOTZLUMYB4O7BMCXCTIRC","json":"https://pith.science/pith/ZAVCFJOTZLUMYB4O7BMCXCTIRC.json","graph_json":"https://pith.science/api/pith-number/ZAVCFJOTZLUMYB4O7BMCXCTIRC/graph.json","events_json":"https://pith.science/api/pith-number/ZAVCFJOTZLUMYB4O7BMCXCTIRC/events.json","paper":"https://pith.science/paper/ZAVCFJOT"},"agent_actions":{"view_html":"https://pith.science/pith/ZAVCFJOTZLUMYB4O7BMCXCTIRC","download_json":"https://pith.science/pith/ZAVCFJOTZLUMYB4O7BMCXCTIRC.json","view_paper":"https://pith.science/paper/ZAVCFJOT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.08928&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAVCFJOTZLUMYB4O7BMCXCTIRC/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAVCFJOTZLUMYB4O7BMCXCTIRC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAVCFJOTZLUMYB4O7BMCXCTIRC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAVCFJOTZLUMYB4O7BMCXCTIRC/action/storage_attestation","attest_author":"https://pith.science/pith/ZAVCFJOTZLUMYB4O7BMCXCTIRC/action/author_attestation","sign_citation":"https://pith.science/pith/ZAVCFJOTZLUMYB4O7BMCXCTIRC/action/citation_signature","submit_replication":"https://pith.science/pith/ZAVCFJOTZLUMYB4O7BMCXCTIRC/action/replication_record"}},"created_at":"2026-05-17T23:42:47.376788+00:00","updated_at":"2026-05-17T23:42:47.376788+00:00"}