{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:UCU7JKISEX6Z5HAOXP6JS53GVB","short_pith_number":"pith:UCU7JKIS","schema_version":"1.0","canonical_sha256":"a0a9f4a91225fd9e9c0ebbfc997766a875beb1d240e1caabcfc7f311cd830b89","source":{"kind":"arxiv","id":"1709.06166","version":1},"attestation_state":"computed","paper":{"title":"DropoutDAgger: A Bayesian Approach to Safe Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Katherine Driggs-Campbell, Kunal Menda, Mykel J. Kochenderfer","submitted_at":"2017-09-18T20:51:53Z","abstract_excerpt":"While imitation learning is becoming common practice in robotics, this approach often suffers from data mismatch and compounding errors. DAgger is an iterative algorithm that addresses these issues by continually aggregating training data from both the expert and novice policies, but does not consider the impact of safety. We present a probabilistic extension to DAgger, which uses the distribution over actions provided by the novice policy, for a given observation. Our method, which we call DropoutDAgger, uses dropout to train the novice as a Bayesian neural network that provides insight to it"},"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":"1709.06166","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2017-09-18T20:51:53Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"1151e04298056a66580afc0e463dfe103e7bed8ec4931c21505d1f06442bb85c","abstract_canon_sha256":"ce5bb8569156664b0e84ca0e9c40a10e67f345e259cc0b3b328450efa5c68501"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:54.172484Z","signature_b64":"SSsjNQylSjQ2lUluruX4cRs7BLOsl6RVvL7lcyJC8peeSvZ75/bszO3JVnyKeau35THpuLJuIpz8cXXD2I2/CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0a9f4a91225fd9e9c0ebbfc997766a875beb1d240e1caabcfc7f311cd830b89","last_reissued_at":"2026-05-18T00:34:54.171770Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:54.171770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DropoutDAgger: A Bayesian Approach to Safe Imitation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.AI","authors_text":"Katherine Driggs-Campbell, Kunal Menda, Mykel J. Kochenderfer","submitted_at":"2017-09-18T20:51:53Z","abstract_excerpt":"While imitation learning is becoming common practice in robotics, this approach often suffers from data mismatch and compounding errors. DAgger is an iterative algorithm that addresses these issues by continually aggregating training data from both the expert and novice policies, but does not consider the impact of safety. We present a probabilistic extension to DAgger, which uses the distribution over actions provided by the novice policy, for a given observation. Our method, which we call DropoutDAgger, uses dropout to train the novice as a Bayesian neural network that provides insight to it"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.06166","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":"1709.06166","created_at":"2026-05-18T00:34:54.171896+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.06166v1","created_at":"2026-05-18T00:34:54.171896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.06166","created_at":"2026-05-18T00:34:54.171896+00:00"},{"alias_kind":"pith_short_12","alias_value":"UCU7JKISEX6Z","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"UCU7JKISEX6Z5HAO","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"UCU7JKIS","created_at":"2026-05-18T12:31:46.661854+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/UCU7JKISEX6Z5HAOXP6JS53GVB","json":"https://pith.science/pith/UCU7JKISEX6Z5HAOXP6JS53GVB.json","graph_json":"https://pith.science/api/pith-number/UCU7JKISEX6Z5HAOXP6JS53GVB/graph.json","events_json":"https://pith.science/api/pith-number/UCU7JKISEX6Z5HAOXP6JS53GVB/events.json","paper":"https://pith.science/paper/UCU7JKIS"},"agent_actions":{"view_html":"https://pith.science/pith/UCU7JKISEX6Z5HAOXP6JS53GVB","download_json":"https://pith.science/pith/UCU7JKISEX6Z5HAOXP6JS53GVB.json","view_paper":"https://pith.science/paper/UCU7JKIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.06166&json=true","fetch_graph":"https://pith.science/api/pith-number/UCU7JKISEX6Z5HAOXP6JS53GVB/graph.json","fetch_events":"https://pith.science/api/pith-number/UCU7JKISEX6Z5HAOXP6JS53GVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UCU7JKISEX6Z5HAOXP6JS53GVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UCU7JKISEX6Z5HAOXP6JS53GVB/action/storage_attestation","attest_author":"https://pith.science/pith/UCU7JKISEX6Z5HAOXP6JS53GVB/action/author_attestation","sign_citation":"https://pith.science/pith/UCU7JKISEX6Z5HAOXP6JS53GVB/action/citation_signature","submit_replication":"https://pith.science/pith/UCU7JKISEX6Z5HAOXP6JS53GVB/action/replication_record"}},"created_at":"2026-05-18T00:34:54.171896+00:00","updated_at":"2026-05-18T00:34:54.171896+00:00"}