{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:LI7RYNUBFFGLDX4N56CF24G7ZG","short_pith_number":"pith:LI7RYNUB","schema_version":"1.0","canonical_sha256":"5a3f1c3681294cb1df8def845d70dfc9835cc54a88a67b949e7c265ad96f44b6","source":{"kind":"arxiv","id":"2008.03525","version":1},"attestation_state":"computed","paper":{"title":"Non-Adversarial Imitation Learning and its Connections to Adversarial Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.RO","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gerhard Neumann, Oleg Arenz","submitted_at":"2020-08-08T13:43:06Z","abstract_excerpt":"Many modern methods for imitation learning and inverse reinforcement learning, such as GAIL or AIRL, are based on an adversarial formulation. These methods apply GANs to match the expert's distribution over states and actions with the implicit state-action distribution induced by the agent's policy. However, by framing imitation learning as a saddle point problem, adversarial methods can suffer from unstable optimization, and convergence can only be shown for small policy updates. We address these problems by proposing a framework for non-adversarial imitation learning. The resulting algorithm"},"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":"2008.03525","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-08T13:43:06Z","cross_cats_sorted":["cs.IT","cs.RO","math.IT","stat.ML"],"title_canon_sha256":"2146b2400a76d9a7e0a113c9dd62ddec683f1a87e8c6bdf3cbedae868c9da19c","abstract_canon_sha256":"3d8fec8b0b2db9cb0c482c0d6572c3213c9802f376690b92c8aabd2369790ae9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:42.747348Z","signature_b64":"VrBWrDSJp3/nPBvGo2/Cp5IyiZ9NTMNhIJMdtW13DLuSRQuf6wp5ZWZec8prkxAK5iv9UA0wNPI2KxRfEYgUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a3f1c3681294cb1df8def845d70dfc9835cc54a88a67b949e7c265ad96f44b6","last_reissued_at":"2026-07-05T01:25:42.746907Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:42.746907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Non-Adversarial Imitation Learning and its Connections to Adversarial Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.RO","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Gerhard Neumann, Oleg Arenz","submitted_at":"2020-08-08T13:43:06Z","abstract_excerpt":"Many modern methods for imitation learning and inverse reinforcement learning, such as GAIL or AIRL, are based on an adversarial formulation. These methods apply GANs to match the expert's distribution over states and actions with the implicit state-action distribution induced by the agent's policy. However, by framing imitation learning as a saddle point problem, adversarial methods can suffer from unstable optimization, and convergence can only be shown for small policy updates. We address these problems by proposing a framework for non-adversarial imitation learning. The resulting algorithm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.03525","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.03525/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":"2008.03525","created_at":"2026-07-05T01:25:42.746963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.03525v1","created_at":"2026-07-05T01:25:42.746963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.03525","created_at":"2026-07-05T01:25:42.746963+00:00"},{"alias_kind":"pith_short_12","alias_value":"LI7RYNUBFFGL","created_at":"2026-07-05T01:25:42.746963+00:00"},{"alias_kind":"pith_short_16","alias_value":"LI7RYNUBFFGLDX4N","created_at":"2026-07-05T01:25:42.746963+00:00"},{"alias_kind":"pith_short_8","alias_value":"LI7RYNUB","created_at":"2026-07-05T01:25:42.746963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11020","citing_title":"Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LI7RYNUBFFGLDX4N56CF24G7ZG","json":"https://pith.science/pith/LI7RYNUBFFGLDX4N56CF24G7ZG.json","graph_json":"https://pith.science/api/pith-number/LI7RYNUBFFGLDX4N56CF24G7ZG/graph.json","events_json":"https://pith.science/api/pith-number/LI7RYNUBFFGLDX4N56CF24G7ZG/events.json","paper":"https://pith.science/paper/LI7RYNUB"},"agent_actions":{"view_html":"https://pith.science/pith/LI7RYNUBFFGLDX4N56CF24G7ZG","download_json":"https://pith.science/pith/LI7RYNUBFFGLDX4N56CF24G7ZG.json","view_paper":"https://pith.science/paper/LI7RYNUB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.03525&json=true","fetch_graph":"https://pith.science/api/pith-number/LI7RYNUBFFGLDX4N56CF24G7ZG/graph.json","fetch_events":"https://pith.science/api/pith-number/LI7RYNUBFFGLDX4N56CF24G7ZG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LI7RYNUBFFGLDX4N56CF24G7ZG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LI7RYNUBFFGLDX4N56CF24G7ZG/action/storage_attestation","attest_author":"https://pith.science/pith/LI7RYNUBFFGLDX4N56CF24G7ZG/action/author_attestation","sign_citation":"https://pith.science/pith/LI7RYNUBFFGLDX4N56CF24G7ZG/action/citation_signature","submit_replication":"https://pith.science/pith/LI7RYNUBFFGLDX4N56CF24G7ZG/action/replication_record"}},"created_at":"2026-07-05T01:25:42.746963+00:00","updated_at":"2026-07-05T01:25:42.746963+00:00"}