{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SRUBPYC7CC2RPMXKJTNODKHLLF","short_pith_number":"pith:SRUBPYC7","schema_version":"1.0","canonical_sha256":"946817e05f10b517b2ea4cdae1a8eb5976ea5fa6fb77753fdd98545a28160ea2","source":{"kind":"arxiv","id":"2108.04763","version":2},"attestation_state":"computed","paper":{"title":"Imitation Learning by Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kamil Ciosek","submitted_at":"2021-08-10T16:14:41Z","abstract_excerpt":"Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical analysis both certifies the recovery of expert reward and bounds the total variation distance between the expert and the imitation learner, showing a link to adversarial imitation learning. We conduct experiments which confirm that our reduction works well in practice for continuous control tasks."},"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":"2108.04763","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-08-10T16:14:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f1577fe436114dd4f38305c237117cea30479ed3b12aa0c4f7811131a6bcc03c","abstract_canon_sha256":"6e2d9b6ce316416659c35fe56191e17228a79a217cc34a239d306bd76d60a47e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:12.602220Z","signature_b64":"/luxQLtE9Pvb1wbkgvyaTNm81c3S7Y4MU/tSHKeUKHJxS3Iu0cORRGQ/k+xhhHTXHjTqM8PQmNOby7KYpE9VBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"946817e05f10b517b2ea4cdae1a8eb5976ea5fa6fb77753fdd98545a28160ea2","last_reissued_at":"2026-07-05T04:05:12.601768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:12.601768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imitation Learning by Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Kamil Ciosek","submitted_at":"2021-08-10T16:14:41Z","abstract_excerpt":"Imitation learning algorithms learn a policy from demonstrations of expert behavior. We show that, for deterministic experts, imitation learning can be done by reduction to reinforcement learning with a stationary reward. Our theoretical analysis both certifies the recovery of expert reward and bounds the total variation distance between the expert and the imitation learner, showing a link to adversarial imitation learning. We conduct experiments which confirm that our reduction works well in practice for continuous control tasks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.04763","kind":"arxiv","version":2},"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/2108.04763/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":"2108.04763","created_at":"2026-07-05T04:05:12.601824+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.04763v2","created_at":"2026-07-05T04:05:12.601824+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.04763","created_at":"2026-07-05T04:05:12.601824+00:00"},{"alias_kind":"pith_short_12","alias_value":"SRUBPYC7CC2R","created_at":"2026-07-05T04:05:12.601824+00:00"},{"alias_kind":"pith_short_16","alias_value":"SRUBPYC7CC2RPMXK","created_at":"2026-07-05T04:05:12.601824+00:00"},{"alias_kind":"pith_short_8","alias_value":"SRUBPYC7","created_at":"2026-07-05T04:05:12.601824+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/SRUBPYC7CC2RPMXKJTNODKHLLF","json":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF.json","graph_json":"https://pith.science/api/pith-number/SRUBPYC7CC2RPMXKJTNODKHLLF/graph.json","events_json":"https://pith.science/api/pith-number/SRUBPYC7CC2RPMXKJTNODKHLLF/events.json","paper":"https://pith.science/paper/SRUBPYC7"},"agent_actions":{"view_html":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF","download_json":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF.json","view_paper":"https://pith.science/paper/SRUBPYC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.04763&json=true","fetch_graph":"https://pith.science/api/pith-number/SRUBPYC7CC2RPMXKJTNODKHLLF/graph.json","fetch_events":"https://pith.science/api/pith-number/SRUBPYC7CC2RPMXKJTNODKHLLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/action/storage_attestation","attest_author":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/action/author_attestation","sign_citation":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/action/citation_signature","submit_replication":"https://pith.science/pith/SRUBPYC7CC2RPMXKJTNODKHLLF/action/replication_record"}},"created_at":"2026-07-05T04:05:12.601824+00:00","updated_at":"2026-07-05T04:05:12.601824+00:00"}