{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:B7DUAFU6ZF74SS4SYPJAGG2DIT","short_pith_number":"pith:B7DUAFU6","schema_version":"1.0","canonical_sha256":"0fc740169ec97fc94b92c3d2031b4344d89abf719cd8283482be268cc5216b97","source":{"kind":"arxiv","id":"1605.08478","version":1},"attestation_state":"computed","paper":{"title":"Model-Free Imitation Learning with Policy Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jayesh K. Gupta, Jonathan Ho, Stefano Ermon","submitted_at":"2016-05-26T23:43:32Z","abstract_excerpt":"In imitation learning, an agent learns how to behave in an environment with an unknown cost function by mimicking expert demonstrations. Existing imitation learning algorithms typically involve solving a sequence of planning or reinforcement learning problems. Such algorithms are therefore not directly applicable to large, high-dimensional environments, and their performance can significantly degrade if the planning problems are not solved to optimality. Under the apprenticeship learning formalism, we develop alternative model-free algorithms for finding a parameterized stochastic policy that "},"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":"1605.08478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2016-05-26T23:43:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93944bd1a92ad28f87b2458e2f688cf89d797e13ce88a713fff5569dcd682c40","abstract_canon_sha256":"1f377be0c7ed6d1fee48ba0c648011195cf82ab840ab73f3cbcac54dbec32cc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:22.381141Z","signature_b64":"S2fAxWeuZ6fK/Jh7RZwY7RS9RSkqOnMmYLQvzI58GKoc6iNW0RjXANixPyFIJDVzSI66/ikQagyiWQ3GAiIIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fc740169ec97fc94b92c3d2031b4344d89abf719cd8283482be268cc5216b97","last_reissued_at":"2026-05-18T01:12:22.380792Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:22.380792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Free Imitation Learning with Policy Optimization","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Jayesh K. Gupta, Jonathan Ho, Stefano Ermon","submitted_at":"2016-05-26T23:43:32Z","abstract_excerpt":"In imitation learning, an agent learns how to behave in an environment with an unknown cost function by mimicking expert demonstrations. Existing imitation learning algorithms typically involve solving a sequence of planning or reinforcement learning problems. Such algorithms are therefore not directly applicable to large, high-dimensional environments, and their performance can significantly degrade if the planning problems are not solved to optimality. Under the apprenticeship learning formalism, we develop alternative model-free algorithms for finding a parameterized stochastic policy that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.08478","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1605.08478","created_at":"2026-05-18T01:12:22.380857+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.08478v1","created_at":"2026-05-18T01:12:22.380857+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.08478","created_at":"2026-05-18T01:12:22.380857+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7DUAFU6ZF74","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7DUAFU6ZF74SS4S","created_at":"2026-05-18T12:30:07.202191+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7DUAFU6","created_at":"2026-05-18T12:30:07.202191+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/B7DUAFU6ZF74SS4SYPJAGG2DIT","json":"https://pith.science/pith/B7DUAFU6ZF74SS4SYPJAGG2DIT.json","graph_json":"https://pith.science/api/pith-number/B7DUAFU6ZF74SS4SYPJAGG2DIT/graph.json","events_json":"https://pith.science/api/pith-number/B7DUAFU6ZF74SS4SYPJAGG2DIT/events.json","paper":"https://pith.science/paper/B7DUAFU6"},"agent_actions":{"view_html":"https://pith.science/pith/B7DUAFU6ZF74SS4SYPJAGG2DIT","download_json":"https://pith.science/pith/B7DUAFU6ZF74SS4SYPJAGG2DIT.json","view_paper":"https://pith.science/paper/B7DUAFU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.08478&json=true","fetch_graph":"https://pith.science/api/pith-number/B7DUAFU6ZF74SS4SYPJAGG2DIT/graph.json","fetch_events":"https://pith.science/api/pith-number/B7DUAFU6ZF74SS4SYPJAGG2DIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7DUAFU6ZF74SS4SYPJAGG2DIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7DUAFU6ZF74SS4SYPJAGG2DIT/action/storage_attestation","attest_author":"https://pith.science/pith/B7DUAFU6ZF74SS4SYPJAGG2DIT/action/author_attestation","sign_citation":"https://pith.science/pith/B7DUAFU6ZF74SS4SYPJAGG2DIT/action/citation_signature","submit_replication":"https://pith.science/pith/B7DUAFU6ZF74SS4SYPJAGG2DIT/action/replication_record"}},"created_at":"2026-05-18T01:12:22.380857+00:00","updated_at":"2026-05-18T01:12:22.380857+00:00"}