{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4H5OFESRQKCXHKN76YGXK26WFI","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":"da229367a4f916bfb8b7e7ebaa9dcf2989ad123e46a655e1df3505b4ba9fb041","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T22:28:50Z","title_canon_sha256":"8c05223298de86e829f6c821207ab0ebee61f06595db92632983ed55bbb77191"},"schema_version":"1.0","source":{"id":"2001.07798","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.07798","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"arxiv_version","alias_value":"2001.07798v4","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07798","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"pith_short_12","alias_value":"4H5OFESRQKCX","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"pith_short_16","alias_value":"4H5OFESRQKCXHKN7","created_at":"2026-07-05T01:50:17Z"},{"alias_kind":"pith_short_8","alias_value":"4H5OFESR","created_at":"2026-07-05T01:50:17Z"}],"graph_snapshots":[{"event_id":"sha256:2e45893a042d23906dd59a04226f14c591ece009f8b52532cc73f00ee11c8fcf","target":"graph","created_at":"2026-07-05T01:50:17Z","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/2001.07798/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning is the problem of recovering an expert policy without access to a reward signal. Behavior cloning and GAIL are two widely used methods for performing imitation learning. Behavior cloning converges in a few iterations but doesn't achieve peak performance due to its inherent iid assumption about the state-action distribution. GAIL addresses the issue by accounting for the temporal dependencies when performing a state distribution matching between the agent and the expert. Although GAIL is sample efficient in the number of expert trajectories required, it is still not very samp","authors_text":"Changliu Liu, Katia Sycara, Rohit Jena","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T22:28:50Z","title":"Augmenting GAIL with BC for sample efficient imitation learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07798","kind":"arxiv","version":4},"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":"sha256:726b37db9f69756a9d9279c7091691e4fbb208d60608eff157f07e9b2d8e9fc2","target":"record","created_at":"2026-07-05T01:50:17Z","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":"da229367a4f916bfb8b7e7ebaa9dcf2989ad123e46a655e1df3505b4ba9fb041","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T22:28:50Z","title_canon_sha256":"8c05223298de86e829f6c821207ab0ebee61f06595db92632983ed55bbb77191"},"schema_version":"1.0","source":{"id":"2001.07798","kind":"arxiv","version":4}},"canonical_sha256":"e1fae29251828573a9bff60d756bd62a281da58c7dc72c4a3f24b760cd33c504","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1fae29251828573a9bff60d756bd62a281da58c7dc72c4a3f24b760cd33c504","first_computed_at":"2026-07-05T01:50:17.054039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:50:17.054039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2wigJREUWbHdZsVx0ZFh5qmam79tjjkZ/i46DAoaOrUzC0VioE4kmh+52gxFYd76cxJdoueacet0wh/0VgzABQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:50:17.054456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.07798","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:726b37db9f69756a9d9279c7091691e4fbb208d60608eff157f07e9b2d8e9fc2","sha256:2e45893a042d23906dd59a04226f14c591ece009f8b52532cc73f00ee11c8fcf"],"state_sha256":"94121bf49126dc6b89f445d24abe2ba8f38d0db922228cb41d27b508ad348808"}