{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EH7KTUT3PMHKRW3F37GKAIDUSJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bb139a1f1f3358c8f77d7cbb4e3b381fe4270765d35df06d79c9b6cb1f71a6ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-11T06:06:43Z","title_canon_sha256":"9ca5daad41d3c6791975edc13dadd33604c218c763d1e2116b661c961c8ebd7f"},"schema_version":"1.0","source":{"id":"1806.03820","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.03820","created_at":"2026-05-18T00:13:41Z"},{"alias_kind":"arxiv_version","alias_value":"1806.03820v1","created_at":"2026-05-18T00:13:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03820","created_at":"2026-05-18T00:13:41Z"},{"alias_kind":"pith_short_12","alias_value":"EH7KTUT3PMHK","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EH7KTUT3PMHKRW3F","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EH7KTUT3","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:0984193de06dcf6246ddcf410187ccae076bc824c9668b4903ac168de3d917b4","target":"graph","created_at":"2026-05-18T00:13:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"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","authors_text":"Anca D. Dragan, Dhruv Malik, Dylan Hadfield-Menell, Jaime F. Fisac, Malayandi Palaniappan, Stuart Russell","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-11T06:06:43Z","title":"An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03820","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:09e21bbfa322a9837e843d24aff002bd8a0d43e48869caddcd762454eabb2af3","target":"record","created_at":"2026-05-18T00:13:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bb139a1f1f3358c8f77d7cbb4e3b381fe4270765d35df06d79c9b6cb1f71a6ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-06-11T06:06:43Z","title_canon_sha256":"9ca5daad41d3c6791975edc13dadd33604c218c763d1e2116b661c961c8ebd7f"},"schema_version":"1.0","source":{"id":"1806.03820","kind":"arxiv","version":1}},"canonical_sha256":"21fea9d27b7b0ea8db65dfcca02074925252896fa93c011c5ac82a627aef9355","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21fea9d27b7b0ea8db65dfcca02074925252896fa93c011c5ac82a627aef9355","first_computed_at":"2026-05-18T00:13:41.990940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:41.990940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cNAhYHBBwxABd8Eh0/oj7g9d45+t4dNfrtfFq5UOXxYfI+fBfq/jbRGkfNH+yFli3ayQR+cyf+hgDcRFQrciDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:41.991587Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.03820","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09e21bbfa322a9837e843d24aff002bd8a0d43e48869caddcd762454eabb2af3","sha256:0984193de06dcf6246ddcf410187ccae076bc824c9668b4903ac168de3d917b4"],"state_sha256":"516b97860f087333b90785e2c13133507355b39e99b55f464ec4b9bd10adff17"}