{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:47QSMHUHY5KM3JPTWHUXEJR4EA","short_pith_number":"pith:47QSMHUH","canonical_record":{"source":{"id":"1903.03234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T00:54:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a2aa9beac6a2490fc3a1d6557c73488b4fbd8ccb667dc98acfd8b45f68631091","abstract_canon_sha256":"c8f480a8006ad1d0b0143ad6eb4bbf522e95b83cdcf0c95bf390dcf71060e4c1"},"schema_version":"1.0"},"canonical_sha256":"e7e1261e87c754cda5f3b1e972263c2001d7dcf3c064e530f215b8488097c79a","source":{"kind":"arxiv","id":"1903.03234","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:47QSMHUHY5KM3JPTWHUXEJR4EA","target":"record","payload":{"canonical_record":{"source":{"id":"1903.03234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-03-08T00:54:49Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"a2aa9beac6a2490fc3a1d6557c73488b4fbd8ccb667dc98acfd8b45f68631091","abstract_canon_sha256":"c8f480a8006ad1d0b0143ad6eb4bbf522e95b83cdcf0c95bf390dcf71060e4c1"},"schema_version":"1.0"},"canonical_sha256":"e7e1261e87c754cda5f3b1e972263c2001d7dcf3c064e530f215b8488097c79a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:46.108569Z","signature_b64":"Uo4d6Wd+MA/lDukWlxJkofWCrawYfDHd//xITmQ8gKUHwdU2r4xMW8fUp6d3tTBXu7sCNh2CWvrstyGfIbj7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7e1261e87c754cda5f3b1e972263c2001d7dcf3c064e530f215b8488097c79a","last_reissued_at":"2026-05-17T23:51:46.107899Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:46.107899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.03234","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dD5mPAez5SkzO6S2thLERqkF1pr9kzWx2pVqnFGR18raGEGss7itUT7ZyISRacMSAVAnSU1VvfCxHKlxIXGpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T02:04:43.918730Z"},"content_sha256":"16cc64a69f9131bc6044a9b7b9fa97acb8dc11bd5f4a2f564330cca33428a3ff","schema_version":"1.0","event_id":"sha256:16cc64a69f9131bc6044a9b7b9fa97acb8dc11bd5f4a2f564330cca33428a3ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:47QSMHUHY5KM3JPTWHUXEJR4EA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dyna-AIL : Adversarial Imitation Learning by Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Pulkit Mathur, Srinivasan Sivanandan, Vaibhav Saxena","submitted_at":"2019-03-08T00:54:49Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03234","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uOazF6G5gDtbfPZtba2O6mmjZAYCg2kAGHyLY+8w7nu6vQyu4hs5rwhm7saXMkLUXg3oL9tpiex3fWp/cxMqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T02:04:43.919177Z"},"content_sha256":"bfdba3267a525375c22107960786cf39c5ab5533b84c098d5adf3c50d6ac4851","schema_version":"1.0","event_id":"sha256:bfdba3267a525375c22107960786cf39c5ab5533b84c098d5adf3c50d6ac4851"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/47QSMHUHY5KM3JPTWHUXEJR4EA/bundle.json","state_url":"https://pith.science/pith/47QSMHUHY5KM3JPTWHUXEJR4EA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/47QSMHUHY5KM3JPTWHUXEJR4EA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-11T02:04:43Z","links":{"resolver":"https://pith.science/pith/47QSMHUHY5KM3JPTWHUXEJR4EA","bundle":"https://pith.science/pith/47QSMHUHY5KM3JPTWHUXEJR4EA/bundle.json","state":"https://pith.science/pith/47QSMHUHY5KM3JPTWHUXEJR4EA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/47QSMHUHY5KM3JPTWHUXEJR4EA/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VVEroVsNMmc96KbXgsmV0Eao5SJTHTpanXA94H1AyE/tC4ljPRriaMQaaBsBqvMkscglJdIKH2uuHYAwHJIHCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T02:04:43.922705Z","bundle_sha256":"224c06320b5aec9a2d77c0a86c36759445c81918721a81f69bc82517f973ae2a"}}