{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FISLBZVY4ZICBZ27LACZD7BPSD","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":"00f8972b8cdaa412bbde5f934689812350f5ba622fc1de196d04b6cb127d8279","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T18:57:11Z","title_canon_sha256":"c209fc9ca2e97f1be8f6b57c7a32d099644728746c5facc3836fd5979dd7cdb3"},"schema_version":"1.0","source":{"id":"2103.03236","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.03236","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"arxiv_version","alias_value":"2103.03236v2","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.03236","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_12","alias_value":"FISLBZVY4ZIC","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_16","alias_value":"FISLBZVY4ZICBZ27","created_at":"2026-07-05T02:48:21Z"},{"alias_kind":"pith_short_8","alias_value":"FISLBZVY","created_at":"2026-07-05T02:48:21Z"}],"graph_snapshots":[{"event_id":"sha256:0aab47ea8f02da30e3984b8dd338090bdd9ab097abb54191de3169eae5f0a1dd","target":"graph","created_at":"2026-07-05T02:48:21Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.03236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching. At its core, our classification scheme is based on whether the learner attempts to match (1) reward or (2) action-value moments of the expert's behavior, with each option leading to differing algorithmic approaches. By considering adversarially chosen divergences between learner and expert behavior, we are able to derive bounds on policy performance that apply for all algorithms in each of these classes, the first to our knowledge. We also introduce the notion of moment r","authors_text":"Gokul Swamy, J. Andrew Bagnell, Sanjiban Choudhury, Zhiwei Steven Wu","cross_cats":["cs.RO","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T18:57:11Z","title":"Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.03236","kind":"arxiv","version":2},"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":"sha256:7d413a35af45bb0feb17a3199cfff9cd8dc89150b52f4d291448d8db4d4c6706","target":"record","created_at":"2026-07-05T02:48:21Z","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":"00f8972b8cdaa412bbde5f934689812350f5ba622fc1de196d04b6cb127d8279","cross_cats_sorted":["cs.RO","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-03-04T18:57:11Z","title_canon_sha256":"c209fc9ca2e97f1be8f6b57c7a32d099644728746c5facc3836fd5979dd7cdb3"},"schema_version":"1.0","source":{"id":"2103.03236","kind":"arxiv","version":2}},"canonical_sha256":"2a24b0e6b8e65020e75f580591fc2f90c4aad61be43b88d0a39013a0dd7cf41d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a24b0e6b8e65020e75f580591fc2f90c4aad61be43b88d0a39013a0dd7cf41d","first_computed_at":"2026-07-05T02:48:21.869533Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:21.869533Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/NTgsHC8AG6SVn+aSWzkrO27A6rlhDVSUu0gF0F79R+qRNBySmtmkxbpaaYoWPxx8sfjVBwNla3EQEHSueNIDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:21.869897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.03236","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d413a35af45bb0feb17a3199cfff9cd8dc89150b52f4d291448d8db4d4c6706","sha256:0aab47ea8f02da30e3984b8dd338090bdd9ab097abb54191de3169eae5f0a1dd"],"state_sha256":"e1aca3c4727c4823b6ce6be5c389cc8396f9fc7bf02987787085647a97d24871"}