{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4H5OFESRQKCXHKN76YGXK26WFI","short_pith_number":"pith:4H5OFESR","schema_version":"1.0","canonical_sha256":"e1fae29251828573a9bff60d756bd62a281da58c7dc72c4a3f24b760cd33c504","source":{"kind":"arxiv","id":"2001.07798","version":4},"attestation_state":"computed","paper":{"title":"Augmenting GAIL with BC for sample efficient imitation learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Katia Sycara, Rohit Jena","submitted_at":"2020-01-21T22:28:50Z","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"},"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":"2001.07798","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-21T22:28:50Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"8c05223298de86e829f6c821207ab0ebee61f06595db92632983ed55bbb77191","abstract_canon_sha256":"da229367a4f916bfb8b7e7ebaa9dcf2989ad123e46a655e1df3505b4ba9fb041"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:17.054456Z","signature_b64":"2wigJREUWbHdZsVx0ZFh5qmam79tjjkZ/i46DAoaOrUzC0VioE4kmh+52gxFYd76cxJdoueacet0wh/0VgzABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1fae29251828573a9bff60d756bd62a281da58c7dc72c4a3f24b760cd33c504","last_reissued_at":"2026-07-05T01:50:17.054039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:17.054039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Augmenting GAIL with BC for sample efficient imitation learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Katia Sycara, Rohit Jena","submitted_at":"2020-01-21T22:28:50Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.07798","kind":"arxiv","version":4},"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/2001.07798/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":"2001.07798","created_at":"2026-07-05T01:50:17.054089+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.07798v4","created_at":"2026-07-05T01:50:17.054089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.07798","created_at":"2026-07-05T01:50:17.054089+00:00"},{"alias_kind":"pith_short_12","alias_value":"4H5OFESRQKCX","created_at":"2026-07-05T01:50:17.054089+00:00"},{"alias_kind":"pith_short_16","alias_value":"4H5OFESRQKCXHKN7","created_at":"2026-07-05T01:50:17.054089+00:00"},{"alias_kind":"pith_short_8","alias_value":"4H5OFESR","created_at":"2026-07-05T01:50:17.054089+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00044","citing_title":"Creating Hierarchical Dispositions of Needs in an Agent","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI","json":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI.json","graph_json":"https://pith.science/api/pith-number/4H5OFESRQKCXHKN76YGXK26WFI/graph.json","events_json":"https://pith.science/api/pith-number/4H5OFESRQKCXHKN76YGXK26WFI/events.json","paper":"https://pith.science/paper/4H5OFESR"},"agent_actions":{"view_html":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI","download_json":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI.json","view_paper":"https://pith.science/paper/4H5OFESR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.07798&json=true","fetch_graph":"https://pith.science/api/pith-number/4H5OFESRQKCXHKN76YGXK26WFI/graph.json","fetch_events":"https://pith.science/api/pith-number/4H5OFESRQKCXHKN76YGXK26WFI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI/action/storage_attestation","attest_author":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI/action/author_attestation","sign_citation":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI/action/citation_signature","submit_replication":"https://pith.science/pith/4H5OFESRQKCXHKN76YGXK26WFI/action/replication_record"}},"created_at":"2026-07-05T01:50:17.054089+00:00","updated_at":"2026-07-05T01:50:17.054089+00:00"}