{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:47QSMHUHY5KM3JPTWHUXEJR4EA","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":"c8f480a8006ad1d0b0143ad6eb4bbf522e95b83cdcf0c95bf390dcf71060e4c1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T00:54:49Z","title_canon_sha256":"a2aa9beac6a2490fc3a1d6557c73488b4fbd8ccb667dc98acfd8b45f68631091"},"schema_version":"1.0","source":{"id":"1903.03234","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03234","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03234v1","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03234","created_at":"2026-05-17T23:51:46Z"},{"alias_kind":"pith_short_12","alias_value":"47QSMHUHY5KM","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"47QSMHUHY5KM3JPT","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"47QSMHUH","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:bfdba3267a525375c22107960786cf39c5ab5533b84c098d5adf3c50d6ac4851","target":"graph","created_at":"2026-05-17T23:51:46Z","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"},"paper":{"abstract_excerpt":"Adversarial methods for imitation learning have been shown to perform well on various control tasks. However, they require a large number of environment interactions for convergence. In this paper, we propose an end-to-end differentiable adversarial imitation learning algorithm in a Dyna-like framework for switching between model-based planning and model-free learning from expert data. Our results on both discrete and continuous environments show that our approach of using model-based planning along with model-free learning converges to an optimal policy with fewer number of environment intera","authors_text":"Pulkit Mathur, Srinivasan Sivanandan, Vaibhav Saxena","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T00:54:49Z","title":"Dyna-AIL : Adversarial Imitation Learning by Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03234","kind":"arxiv","version":1},"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":"sha256:16cc64a69f9131bc6044a9b7b9fa97acb8dc11bd5f4a2f564330cca33428a3ff","target":"record","created_at":"2026-05-17T23:51:46Z","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":"c8f480a8006ad1d0b0143ad6eb4bbf522e95b83cdcf0c95bf390dcf71060e4c1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T00:54:49Z","title_canon_sha256":"a2aa9beac6a2490fc3a1d6557c73488b4fbd8ccb667dc98acfd8b45f68631091"},"schema_version":"1.0","source":{"id":"1903.03234","kind":"arxiv","version":1}},"canonical_sha256":"e7e1261e87c754cda5f3b1e972263c2001d7dcf3c064e530f215b8488097c79a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7e1261e87c754cda5f3b1e972263c2001d7dcf3c064e530f215b8488097c79a","first_computed_at":"2026-05-17T23:51:46.107899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:46.107899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uo4d6Wd+MA/lDukWlxJkofWCrawYfDHd//xITmQ8gKUHwdU2r4xMW8fUp6d3tTBXu7sCNh2CWvrstyGfIbj7BA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:46.108569Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.03234","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16cc64a69f9131bc6044a9b7b9fa97acb8dc11bd5f4a2f564330cca33428a3ff","sha256:bfdba3267a525375c22107960786cf39c5ab5533b84c098d5adf3c50d6ac4851"],"state_sha256":"c1481b1095ce5bf8b431cd910ed76e04a0e8efc7ec558065e5c9bd6c986b7112"}