{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F57L4X6VQ5QZ3QD2RM3ZNHA2GK","short_pith_number":"pith:F57L4X6V","schema_version":"1.0","canonical_sha256":"2f7ebe5fd587619dc07a8b37969c1a3287eda1f2e3ab9e1b6910dba027669599","source":{"kind":"arxiv","id":"2403.01059","version":1},"attestation_state":"computed","paper":{"title":"Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Austin Juhl, Nathan Larson, Noah Ford, Ryan W. Gardner","submitted_at":"2024-03-02T01:40:37Z","abstract_excerpt":"Machine-learning paradigms such as imitation learning and reinforcement learning can generate highly performant agents in a variety of complex environments. However, commonly used methods require large quantities of data and/or a known reward function. This paper presents a method called Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL) that employs a novel reward structure to improve the performance of imitation-learning agents that have access to only a handful of expert demonstrations. CMZ-DRIL uses reinforcement learning to minimize uncertainty among an ensemble o"},"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":"2403.01059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-02T01:40:37Z","cross_cats_sorted":[],"title_canon_sha256":"234e8b88171bb81f20cd38dc54a5228c9057a58fe00b812fdf4cf47adc77cf15","abstract_canon_sha256":"6ef5d441f2f3bfef01bc8070b21a416605762c7e7594632d20f831aee6c111c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:15.906007Z","signature_b64":"fzk2AiOivX8G6Sw9lIebYIqX45Fu5c2Y8J3em7vvSCWXj+e/wM8eVfgmTnr4BFLSCLmy4B0n3gUoVrby7KfbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f7ebe5fd587619dc07a8b37969c1a3287eda1f2e3ab9e1b6910dba027669599","last_reissued_at":"2026-07-05T07:51:15.905577Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:15.905577Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Austin Juhl, Nathan Larson, Noah Ford, Ryan W. Gardner","submitted_at":"2024-03-02T01:40:37Z","abstract_excerpt":"Machine-learning paradigms such as imitation learning and reinforcement learning can generate highly performant agents in a variety of complex environments. However, commonly used methods require large quantities of data and/or a known reward function. This paper presents a method called Continuous Mean-Zero Disagreement-Regularized Imitation Learning (CMZ-DRIL) that employs a novel reward structure to improve the performance of imitation-learning agents that have access to only a handful of expert demonstrations. CMZ-DRIL uses reinforcement learning to minimize uncertainty among an ensemble o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.01059","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/2403.01059/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":"2403.01059","created_at":"2026-07-05T07:51:15.905639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.01059v1","created_at":"2026-07-05T07:51:15.905639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.01059","created_at":"2026-07-05T07:51:15.905639+00:00"},{"alias_kind":"pith_short_12","alias_value":"F57L4X6VQ5QZ","created_at":"2026-07-05T07:51:15.905639+00:00"},{"alias_kind":"pith_short_16","alias_value":"F57L4X6VQ5QZ3QD2","created_at":"2026-07-05T07:51:15.905639+00:00"},{"alias_kind":"pith_short_8","alias_value":"F57L4X6V","created_at":"2026-07-05T07:51:15.905639+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/F57L4X6VQ5QZ3QD2RM3ZNHA2GK","json":"https://pith.science/pith/F57L4X6VQ5QZ3QD2RM3ZNHA2GK.json","graph_json":"https://pith.science/api/pith-number/F57L4X6VQ5QZ3QD2RM3ZNHA2GK/graph.json","events_json":"https://pith.science/api/pith-number/F57L4X6VQ5QZ3QD2RM3ZNHA2GK/events.json","paper":"https://pith.science/paper/F57L4X6V"},"agent_actions":{"view_html":"https://pith.science/pith/F57L4X6VQ5QZ3QD2RM3ZNHA2GK","download_json":"https://pith.science/pith/F57L4X6VQ5QZ3QD2RM3ZNHA2GK.json","view_paper":"https://pith.science/paper/F57L4X6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.01059&json=true","fetch_graph":"https://pith.science/api/pith-number/F57L4X6VQ5QZ3QD2RM3ZNHA2GK/graph.json","fetch_events":"https://pith.science/api/pith-number/F57L4X6VQ5QZ3QD2RM3ZNHA2GK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F57L4X6VQ5QZ3QD2RM3ZNHA2GK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F57L4X6VQ5QZ3QD2RM3ZNHA2GK/action/storage_attestation","attest_author":"https://pith.science/pith/F57L4X6VQ5QZ3QD2RM3ZNHA2GK/action/author_attestation","sign_citation":"https://pith.science/pith/F57L4X6VQ5QZ3QD2RM3ZNHA2GK/action/citation_signature","submit_replication":"https://pith.science/pith/F57L4X6VQ5QZ3QD2RM3ZNHA2GK/action/replication_record"}},"created_at":"2026-07-05T07:51:15.905639+00:00","updated_at":"2026-07-05T07:51:15.905639+00:00"}