{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XK5KIENF55XVTRUWQXGJD473N4","short_pith_number":"pith:XK5KIENF","schema_version":"1.0","canonical_sha256":"babaa411a5ef6f59c69685cc91f3fb6f27fe977f82fb6b1de53af4461f4b7e56","source":{"kind":"arxiv","id":"1811.08549","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Peysakhovich","submitted_at":"2018-11-19T22:36:53Z","abstract_excerpt":"Inferring a person's goal from their behavior is an important problem in applications of AI (e.g. automated assistants, recommender systems). The workhorse model for this task is the rational actor model - this amounts to assuming that people have stable reward functions, discount the future exponentially, and construct optimal plans. Under the rational actor assumption techniques such as inverse reinforcement learning (IRL) can be used to infer a person's goals from their actions. A competing model is the dual-system model. Here decisions are the result of an interplay between a fast, automat"},"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":"1811.08549","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-19T22:36:53Z","cross_cats_sorted":["cs.AI","cs.GT","stat.ML"],"title_canon_sha256":"a0ff729343f78883c81a61a9eeb78dcbf28932a697df8f521435d6399e6b7109","abstract_canon_sha256":"c8d24d869e3d972bd37978558a67511250c31812926a53130e06587e27f54305"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:19.335535Z","signature_b64":"svjCy/12ncfugIrSgiOPPDNqevdab5y9af0xNCVzceVfa4Q5b0KCkicqBZwgRiY5Z67tJBcITAXUbeNHVirpBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"babaa411a5ef6f59c69685cc91f3fb6f27fe977f82fb6b1de53af4461f4b7e56","last_reissued_at":"2026-05-17T23:51:19.334995Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:19.334995Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning and Inverse Reinforcement Learning with System 1 and System 2","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.GT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Peysakhovich","submitted_at":"2018-11-19T22:36:53Z","abstract_excerpt":"Inferring a person's goal from their behavior is an important problem in applications of AI (e.g. automated assistants, recommender systems). The workhorse model for this task is the rational actor model - this amounts to assuming that people have stable reward functions, discount the future exponentially, and construct optimal plans. Under the rational actor assumption techniques such as inverse reinforcement learning (IRL) can be used to infer a person's goals from their actions. A competing model is the dual-system model. Here decisions are the result of an interplay between a fast, automat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.08549","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":""},"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":"1811.08549","created_at":"2026-05-17T23:51:19.335081+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.08549v2","created_at":"2026-05-17T23:51:19.335081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.08549","created_at":"2026-05-17T23:51:19.335081+00:00"},{"alias_kind":"pith_short_12","alias_value":"XK5KIENF55XV","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XK5KIENF55XVTRUW","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XK5KIENF","created_at":"2026-05-18T12:33:01.666342+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/XK5KIENF55XVTRUWQXGJD473N4","json":"https://pith.science/pith/XK5KIENF55XVTRUWQXGJD473N4.json","graph_json":"https://pith.science/api/pith-number/XK5KIENF55XVTRUWQXGJD473N4/graph.json","events_json":"https://pith.science/api/pith-number/XK5KIENF55XVTRUWQXGJD473N4/events.json","paper":"https://pith.science/paper/XK5KIENF"},"agent_actions":{"view_html":"https://pith.science/pith/XK5KIENF55XVTRUWQXGJD473N4","download_json":"https://pith.science/pith/XK5KIENF55XVTRUWQXGJD473N4.json","view_paper":"https://pith.science/paper/XK5KIENF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.08549&json=true","fetch_graph":"https://pith.science/api/pith-number/XK5KIENF55XVTRUWQXGJD473N4/graph.json","fetch_events":"https://pith.science/api/pith-number/XK5KIENF55XVTRUWQXGJD473N4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XK5KIENF55XVTRUWQXGJD473N4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XK5KIENF55XVTRUWQXGJD473N4/action/storage_attestation","attest_author":"https://pith.science/pith/XK5KIENF55XVTRUWQXGJD473N4/action/author_attestation","sign_citation":"https://pith.science/pith/XK5KIENF55XVTRUWQXGJD473N4/action/citation_signature","submit_replication":"https://pith.science/pith/XK5KIENF55XVTRUWQXGJD473N4/action/replication_record"}},"created_at":"2026-05-17T23:51:19.335081+00:00","updated_at":"2026-05-17T23:51:19.335081+00:00"}