{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2GVYGUZBZRXEAW6DNXKJCEHGXM","short_pith_number":"pith:2GVYGUZB","schema_version":"1.0","canonical_sha256":"d1ab835321cc6e405bc36dd49110e6bb0260533ffa587edf157898426b00093b","source":{"kind":"arxiv","id":"1903.05766","version":1},"attestation_state":"computed","paper":{"title":"Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Changliu Liu, Derek J. Phillips, Jayesh K. Gupta, Katherine Driggs-Campbell, Mykel J. Kochenderfer, Raunak P. Bhattacharyya","submitted_at":"2019-03-14T00:02:03Z","abstract_excerpt":"Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such behaviors arise due to the many local interactions between agents that are not commonly accounted for in imitation learning. This paper proposes Reward Augmented Imitation Learning (RAIL), which integrates reward augmentation into the multi-agent imitation learning framework and allows the designer to specify prior knowledge in a principled fashion. We prove "},"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":"1903.05766","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2019-03-14T00:02:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6fef4f3505a027b87a1b58353b3890083197da9d7dd5d347313b36794ef549fb","abstract_canon_sha256":"691e85cf86c4e53aae509d790b212a5f18cd82772ca8fc3c7f0ec188b1136444"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:16.288508Z","signature_b64":"NcL0igL7ntPM1baAdxogEqM8zk8uwCQJq+UnQFqYA/cDPRm4/Mv4exJO3wFIHM0wP5ZojuXC/2LxVa1aCWnQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1ab835321cc6e405bc36dd49110e6bb0260533ffa587edf157898426b00093b","last_reissued_at":"2026-05-17T23:51:16.288056Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:16.288056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simulating Emergent Properties of Human Driving Behavior Using Multi-Agent Reward Augmented Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.MA","authors_text":"Changliu Liu, Derek J. Phillips, Jayesh K. Gupta, Katherine Driggs-Campbell, Mykel J. Kochenderfer, Raunak P. Bhattacharyya","submitted_at":"2019-03-14T00:02:03Z","abstract_excerpt":"Recent developments in multi-agent imitation learning have shown promising results for modeling the behavior of human drivers. However, it is challenging to capture emergent traffic behaviors that are observed in real-world datasets. Such behaviors arise due to the many local interactions between agents that are not commonly accounted for in imitation learning. This paper proposes Reward Augmented Imitation Learning (RAIL), which integrates reward augmentation into the multi-agent imitation learning framework and allows the designer to specify prior knowledge in a principled fashion. We prove "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05766","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":"1903.05766","created_at":"2026-05-17T23:51:16.288109+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.05766v1","created_at":"2026-05-17T23:51:16.288109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05766","created_at":"2026-05-17T23:51:16.288109+00:00"},{"alias_kind":"pith_short_12","alias_value":"2GVYGUZBZRXE","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2GVYGUZBZRXEAW6D","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2GVYGUZB","created_at":"2026-05-18T12:33:07.085635+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/2GVYGUZBZRXEAW6DNXKJCEHGXM","json":"https://pith.science/pith/2GVYGUZBZRXEAW6DNXKJCEHGXM.json","graph_json":"https://pith.science/api/pith-number/2GVYGUZBZRXEAW6DNXKJCEHGXM/graph.json","events_json":"https://pith.science/api/pith-number/2GVYGUZBZRXEAW6DNXKJCEHGXM/events.json","paper":"https://pith.science/paper/2GVYGUZB"},"agent_actions":{"view_html":"https://pith.science/pith/2GVYGUZBZRXEAW6DNXKJCEHGXM","download_json":"https://pith.science/pith/2GVYGUZBZRXEAW6DNXKJCEHGXM.json","view_paper":"https://pith.science/paper/2GVYGUZB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.05766&json=true","fetch_graph":"https://pith.science/api/pith-number/2GVYGUZBZRXEAW6DNXKJCEHGXM/graph.json","fetch_events":"https://pith.science/api/pith-number/2GVYGUZBZRXEAW6DNXKJCEHGXM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2GVYGUZBZRXEAW6DNXKJCEHGXM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2GVYGUZBZRXEAW6DNXKJCEHGXM/action/storage_attestation","attest_author":"https://pith.science/pith/2GVYGUZBZRXEAW6DNXKJCEHGXM/action/author_attestation","sign_citation":"https://pith.science/pith/2GVYGUZBZRXEAW6DNXKJCEHGXM/action/citation_signature","submit_replication":"https://pith.science/pith/2GVYGUZBZRXEAW6DNXKJCEHGXM/action/replication_record"}},"created_at":"2026-05-17T23:51:16.288109+00:00","updated_at":"2026-05-17T23:51:16.288109+00:00"}