{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SQQXWVUHLEO2KPNHVIXHG4TQHV","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":"1b6879612623bc8a287f5b68f20e9c21b23aa0162a67d7e34b28eb4d407b8352","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T03:08:07Z","title_canon_sha256":"17fde566627867446c7905354e54794693f5d380f5ddb90462b69802ad4b4197"},"schema_version":"1.0","source":{"id":"1905.10948","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10948","created_at":"2026-05-17T23:43:34Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10948v2","created_at":"2026-05-17T23:43:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10948","created_at":"2026-05-17T23:43:34Z"},{"alias_kind":"pith_short_12","alias_value":"SQQXWVUHLEO2","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SQQXWVUHLEO2KPNH","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SQQXWVUH","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:d960bbe2b062a00f535bea62c5b6e729403595198c47727105f923f03fcfcf04","target":"graph","created_at":"2026-05-17T23:43:34Z","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":"We study Imitation Learning (IL) from Observations alone (ILFO) in large-scale MDPs. While most IL algorithms rely on an expert to directly provide actions to the learner, in this setting the expert only supplies sequences of observations. We design a new model-free algorithm for ILFO, Forward Adversarial Imitation Learning (FAIL), which learns a sequence of time-dependent policies by minimizing an Integral Probability Metric between the observation distributions of the expert policy and the learner. FAIL is the first provably efficient algorithm in ILFO setting, which learns a near-optimal po","authors_text":"Anirudh Vemula, Byron Boots, J. Andrew Bagnell, Wen Sun","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T03:08:07Z","title":"Provably Efficient Imitation Learning from Observation Alone"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10948","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:e7836616e0ade46f6b0ee444f0cfdfd0967cc2f90ca86d7e575a12d66da5ba79","target":"record","created_at":"2026-05-17T23:43:34Z","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":"1b6879612623bc8a287f5b68f20e9c21b23aa0162a67d7e34b28eb4d407b8352","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-27T03:08:07Z","title_canon_sha256":"17fde566627867446c7905354e54794693f5d380f5ddb90462b69802ad4b4197"},"schema_version":"1.0","source":{"id":"1905.10948","kind":"arxiv","version":2}},"canonical_sha256":"94217b5687591da53da7aa2e7372703d52fe4820174978e570bc63f39ef52ecf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94217b5687591da53da7aa2e7372703d52fe4820174978e570bc63f39ef52ecf","first_computed_at":"2026-05-17T23:43:34.156938Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:34.156938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d6M8i/m3FTKrr6mmhfx4zNBA/YikTprMlPSUarIfQYjL99t1p4uQuerxXGudB0Vh/6oNqtLaSGRjeNLxIAgFCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:34.157502Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10948","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7836616e0ade46f6b0ee444f0cfdfd0967cc2f90ca86d7e575a12d66da5ba79","sha256:d960bbe2b062a00f535bea62c5b6e729403595198c47727105f923f03fcfcf04"],"state_sha256":"29a486d872b95b19318a4ec7ac2241367f3d87d91452519e936ed9c1f94d230c"}