{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2011:3G2YZKYIRZRCHIC37OWC4CQSJS","short_pith_number":"pith:3G2YZKYI","schema_version":"1.0","canonical_sha256":"d9b58cab088e6223a05bfbac2e0a124cb4c1c775f3da500d8d5034da0e6071f3","source":{"kind":"arxiv","id":"1106.3655","version":2},"attestation_state":"computed","paper":{"title":"Bayesian multitask inverse reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.ML","authors_text":"Christos Dimitrakakis, Constantin Rothkopf","submitted_at":"2011-06-18T15:00:45Z","abstract_excerpt":"We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or as different experts trying to solve the same task. Our main contribution is to formalise the problem as statistical preference elicitation, via a number of structured priors, whose form captures our biases about the relatedness of different tasks or expert policies. In doing so, we introduce a prior on policy optimality, which is more natural to specify. We show that our framework allows us not only to learn to effi"},"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":"1106.3655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2011-06-18T15:00:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2da27dd3b992fa6d9ddad8688d2efd1be8a548d47521d4f3986c01a50ca0ab2a","abstract_canon_sha256":"a7a60333c9dbaaf1c23d4f38807f0c07d0f1d8f4206a478e25c9fce5cf05b18b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:46:31.778217Z","signature_b64":"L957ypCinDf0FZwEXppt5r8Ori8W2Z/av2fZCBgBCnK0X9ckIe8rkTqkN41cn6CXSmR3Mryq40Yor88H4T6tAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9b58cab088e6223a05bfbac2e0a124cb4c1c775f3da500d8d5034da0e6071f3","last_reissued_at":"2026-05-18T03:46:31.776796Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:46:31.776796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian multitask inverse reinforcement learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"stat.ML","authors_text":"Christos Dimitrakakis, Constantin Rothkopf","submitted_at":"2011-06-18T15:00:45Z","abstract_excerpt":"We generalise the problem of inverse reinforcement learning to multiple tasks, from multiple demonstrations. Each one may represent one expert trying to solve a different task, or as different experts trying to solve the same task. Our main contribution is to formalise the problem as statistical preference elicitation, via a number of structured priors, whose form captures our biases about the relatedness of different tasks or expert policies. In doing so, we introduce a prior on policy optimality, which is more natural to specify. We show that our framework allows us not only to learn to effi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.3655","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":"1106.3655","created_at":"2026-05-18T03:46:31.776979+00:00"},{"alias_kind":"arxiv_version","alias_value":"1106.3655v2","created_at":"2026-05-18T03:46:31.776979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.3655","created_at":"2026-05-18T03:46:31.776979+00:00"},{"alias_kind":"pith_short_12","alias_value":"3G2YZKYIRZRC","created_at":"2026-05-18T12:26:18.847500+00:00"},{"alias_kind":"pith_short_16","alias_value":"3G2YZKYIRZRCHIC3","created_at":"2026-05-18T12:26:18.847500+00:00"},{"alias_kind":"pith_short_8","alias_value":"3G2YZKYI","created_at":"2026-05-18T12:26:18.847500+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/3G2YZKYIRZRCHIC37OWC4CQSJS","json":"https://pith.science/pith/3G2YZKYIRZRCHIC37OWC4CQSJS.json","graph_json":"https://pith.science/api/pith-number/3G2YZKYIRZRCHIC37OWC4CQSJS/graph.json","events_json":"https://pith.science/api/pith-number/3G2YZKYIRZRCHIC37OWC4CQSJS/events.json","paper":"https://pith.science/paper/3G2YZKYI"},"agent_actions":{"view_html":"https://pith.science/pith/3G2YZKYIRZRCHIC37OWC4CQSJS","download_json":"https://pith.science/pith/3G2YZKYIRZRCHIC37OWC4CQSJS.json","view_paper":"https://pith.science/paper/3G2YZKYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1106.3655&json=true","fetch_graph":"https://pith.science/api/pith-number/3G2YZKYIRZRCHIC37OWC4CQSJS/graph.json","fetch_events":"https://pith.science/api/pith-number/3G2YZKYIRZRCHIC37OWC4CQSJS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3G2YZKYIRZRCHIC37OWC4CQSJS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3G2YZKYIRZRCHIC37OWC4CQSJS/action/storage_attestation","attest_author":"https://pith.science/pith/3G2YZKYIRZRCHIC37OWC4CQSJS/action/author_attestation","sign_citation":"https://pith.science/pith/3G2YZKYIRZRCHIC37OWC4CQSJS/action/citation_signature","submit_replication":"https://pith.science/pith/3G2YZKYIRZRCHIC37OWC4CQSJS/action/replication_record"}},"created_at":"2026-05-18T03:46:31.776979+00:00","updated_at":"2026-05-18T03:46:31.776979+00:00"}