{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:EH7KTUT3PMHKRW3F37GKAIDUSJ","short_pith_number":"pith:EH7KTUT3","schema_version":"1.0","canonical_sha256":"21fea9d27b7b0ea8db65dfcca02074925252896fa93c011c5ac82a627aef9355","source":{"kind":"arxiv","id":"1806.03820","version":1},"attestation_state":"computed","paper":{"title":"An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anca D. Dragan, Dhruv Malik, Dylan Hadfield-Menell, Jaime F. Fisac, Malayandi Palaniappan, Stuart Russell","submitted_at":"2018-06-11T06:06:43Z","abstract_excerpt":"Our goal is for AI systems to correctly identify and act according to their human user's objectives. Cooperative Inverse Reinforcement Learning (CIRL) formalizes this value alignment problem as a two-player game between a human and robot, in which only the human knows the parameters of the reward function: the robot needs to learn them as the interaction unfolds. Previous work showed that CIRL can be solved as a POMDP, but with an action space size exponential in the size of the reward parameter space. In this work, we exploit a specific property of CIRL---the human is a full information agent"},"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":"1806.03820","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-11T06:06:43Z","cross_cats_sorted":[],"title_canon_sha256":"9ca5daad41d3c6791975edc13dadd33604c218c763d1e2116b661c961c8ebd7f","abstract_canon_sha256":"bb139a1f1f3358c8f77d7cbb4e3b381fe4270765d35df06d79c9b6cb1f71a6ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:41.991587Z","signature_b64":"cNAhYHBBwxABd8Eh0/oj7g9d45+t4dNfrtfFq5UOXxYfI+fBfq/jbRGkfNH+yFli3ayQR+cyf+hgDcRFQrciDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"21fea9d27b7b0ea8db65dfcca02074925252896fa93c011c5ac82a627aef9355","last_reissued_at":"2026-05-18T00:13:41.990940Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:41.990940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Anca D. Dragan, Dhruv Malik, Dylan Hadfield-Menell, Jaime F. Fisac, Malayandi Palaniappan, Stuart Russell","submitted_at":"2018-06-11T06:06:43Z","abstract_excerpt":"Our goal is for AI systems to correctly identify and act according to their human user's objectives. Cooperative Inverse Reinforcement Learning (CIRL) formalizes this value alignment problem as a two-player game between a human and robot, in which only the human knows the parameters of the reward function: the robot needs to learn them as the interaction unfolds. Previous work showed that CIRL can be solved as a POMDP, but with an action space size exponential in the size of the reward parameter space. In this work, we exploit a specific property of CIRL---the human is a full information agent"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03820","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":"1806.03820","created_at":"2026-05-18T00:13:41.991062+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03820v1","created_at":"2026-05-18T00:13:41.991062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03820","created_at":"2026-05-18T00:13:41.991062+00:00"},{"alias_kind":"pith_short_12","alias_value":"EH7KTUT3PMHK","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_16","alias_value":"EH7KTUT3PMHKRW3F","created_at":"2026-05-18T12:32:22.470017+00:00"},{"alias_kind":"pith_short_8","alias_value":"EH7KTUT3","created_at":"2026-05-18T12:32:22.470017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.08928","citing_title":"Learning Reward Functions by Integrating Human Demonstrations and Preferences","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EH7KTUT3PMHKRW3F37GKAIDUSJ","json":"https://pith.science/pith/EH7KTUT3PMHKRW3F37GKAIDUSJ.json","graph_json":"https://pith.science/api/pith-number/EH7KTUT3PMHKRW3F37GKAIDUSJ/graph.json","events_json":"https://pith.science/api/pith-number/EH7KTUT3PMHKRW3F37GKAIDUSJ/events.json","paper":"https://pith.science/paper/EH7KTUT3"},"agent_actions":{"view_html":"https://pith.science/pith/EH7KTUT3PMHKRW3F37GKAIDUSJ","download_json":"https://pith.science/pith/EH7KTUT3PMHKRW3F37GKAIDUSJ.json","view_paper":"https://pith.science/paper/EH7KTUT3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03820&json=true","fetch_graph":"https://pith.science/api/pith-number/EH7KTUT3PMHKRW3F37GKAIDUSJ/graph.json","fetch_events":"https://pith.science/api/pith-number/EH7KTUT3PMHKRW3F37GKAIDUSJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EH7KTUT3PMHKRW3F37GKAIDUSJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EH7KTUT3PMHKRW3F37GKAIDUSJ/action/storage_attestation","attest_author":"https://pith.science/pith/EH7KTUT3PMHKRW3F37GKAIDUSJ/action/author_attestation","sign_citation":"https://pith.science/pith/EH7KTUT3PMHKRW3F37GKAIDUSJ/action/citation_signature","submit_replication":"https://pith.science/pith/EH7KTUT3PMHKRW3F37GKAIDUSJ/action/replication_record"}},"created_at":"2026-05-18T00:13:41.991062+00:00","updated_at":"2026-05-18T00:13:41.991062+00:00"}