{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:S56HPH5K3GASV5CW36FUAYXHVJ","short_pith_number":"pith:S56HPH5K","schema_version":"1.0","canonical_sha256":"977c779faad9812af456df8b4062e7aa7adee46b08ba26b639097130d9bf9369","source":{"kind":"arxiv","id":"2407.10971","version":1},"attestation_state":"computed","paper":{"title":"Walking the Values in Bayesian Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Abate, Konstantinos Gatsis, Michael A. Osborne, Ondrej Bajgar","submitted_at":"2024-07-15T17:59:52Z","abstract_excerpt":"The goal of Bayesian inverse reinforcement learning (IRL) is recovering a posterior distribution over reward functions using a set of demonstrations from an expert optimizing for a reward unknown to the learner. The resulting posterior over rewards can then be used to synthesize an apprentice policy that performs well on the same or a similar task. A key challenge in Bayesian IRL is bridging the computational gap between the hypothesis space of possible rewards and the likelihood, often defined in terms of Q values: vanilla Bayesian IRL needs to solve the costly forward planning problem - goin"},"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":"2407.10971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-07-15T17:59:52Z","cross_cats_sorted":[],"title_canon_sha256":"4c38a4c31046367dcbd26fe3597e9b7c785dd860d81213f8baea6d97f1a70b33","abstract_canon_sha256":"8aff308e8d1d847ac3eb055f961349b28067c8131ea22e4a17f9cf930a818f75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:07.088881Z","signature_b64":"Ah7CPkmMwA94VaogERbrh6ut6bWF5q6J+uNqwEvRJfIGiMBmXJwtlbUswMxaP9ph0vBX8ustgHiSfSgkxwUYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"977c779faad9812af456df8b4062e7aa7adee46b08ba26b639097130d9bf9369","last_reissued_at":"2026-07-05T08:44:07.088379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:07.088379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Walking the Values in Bayesian Inverse Reinforcement Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Abate, Konstantinos Gatsis, Michael A. Osborne, Ondrej Bajgar","submitted_at":"2024-07-15T17:59:52Z","abstract_excerpt":"The goal of Bayesian inverse reinforcement learning (IRL) is recovering a posterior distribution over reward functions using a set of demonstrations from an expert optimizing for a reward unknown to the learner. The resulting posterior over rewards can then be used to synthesize an apprentice policy that performs well on the same or a similar task. A key challenge in Bayesian IRL is bridging the computational gap between the hypothesis space of possible rewards and the likelihood, often defined in terms of Q values: vanilla Bayesian IRL needs to solve the costly forward planning problem - goin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.10971","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.10971/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2407.10971","created_at":"2026-07-05T08:44:07.088439+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.10971v1","created_at":"2026-07-05T08:44:07.088439+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.10971","created_at":"2026-07-05T08:44:07.088439+00:00"},{"alias_kind":"pith_short_12","alias_value":"S56HPH5K3GAS","created_at":"2026-07-05T08:44:07.088439+00:00"},{"alias_kind":"pith_short_16","alias_value":"S56HPH5K3GASV5CW","created_at":"2026-07-05T08:44:07.088439+00:00"},{"alias_kind":"pith_short_8","alias_value":"S56HPH5K","created_at":"2026-07-05T08:44:07.088439+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/S56HPH5K3GASV5CW36FUAYXHVJ","json":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ.json","graph_json":"https://pith.science/api/pith-number/S56HPH5K3GASV5CW36FUAYXHVJ/graph.json","events_json":"https://pith.science/api/pith-number/S56HPH5K3GASV5CW36FUAYXHVJ/events.json","paper":"https://pith.science/paper/S56HPH5K"},"agent_actions":{"view_html":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ","download_json":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ.json","view_paper":"https://pith.science/paper/S56HPH5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.10971&json=true","fetch_graph":"https://pith.science/api/pith-number/S56HPH5K3GASV5CW36FUAYXHVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/S56HPH5K3GASV5CW36FUAYXHVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ/action/storage_attestation","attest_author":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ/action/author_attestation","sign_citation":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ/action/citation_signature","submit_replication":"https://pith.science/pith/S56HPH5K3GASV5CW36FUAYXHVJ/action/replication_record"}},"created_at":"2026-07-05T08:44:07.088439+00:00","updated_at":"2026-07-05T08:44:07.088439+00:00"}