{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HUTQC3JZSDFXPX6CEVXC3OOS3V","short_pith_number":"pith:HUTQC3JZ","schema_version":"1.0","canonical_sha256":"3d27016d3990cb77dfc2256e2db9d2dd4bc958065816195837aed299347ec3cc","source":{"kind":"arxiv","id":"1909.11228","version":1},"attestation_state":"computed","paper":{"title":"Avoidance Learning Using Observational Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Venuto, Doina Precup, Jhelum Chakravorty, Junhao Wang, Leonard Boussioux, Rola Dali, Yoshua Bengio","submitted_at":"2019-09-24T23:37:35Z","abstract_excerpt":"Imitation learning seeks to learn an expert policy from sampled demonstrations. However, in the real world, it is often difficult to find a perfect expert and avoiding dangerous behaviors becomes relevant for safety reasons. We present the idea of \\textit{learning to avoid}, an objective opposite to imitation learning in some sense, where an agent learns to avoid a demonstrator policy given an environment. We define avoidance learning as the process of optimizing the agent's reward while avoiding dangerous behaviors given by a demonstrator. In this work we develop a framework of avoidance lear"},"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":"1909.11228","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-09-24T23:37:35Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0122364b2d6e12d9a4d0867db93be92a30ee29ba7bf8090a990426b0cf962453","abstract_canon_sha256":"b1ba5dc5c04678010f8be62476d9ba6dc0b17f5627584c5f263568969bc426a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:07:09.607609Z","signature_b64":"pXkYR9QAPNC+iyVlAXSgctKTNSX8JsFPoOsnNPS88GTPH3MnUCaQfuDdrUvgCq72Rndidu6f7pNWFAkYtRs6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d27016d3990cb77dfc2256e2db9d2dd4bc958065816195837aed299347ec3cc","last_reissued_at":"2026-07-05T00:07:09.607067Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:07:09.607067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Avoidance Learning Using Observational Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Venuto, Doina Precup, Jhelum Chakravorty, Junhao Wang, Leonard Boussioux, Rola Dali, Yoshua Bengio","submitted_at":"2019-09-24T23:37:35Z","abstract_excerpt":"Imitation learning seeks to learn an expert policy from sampled demonstrations. However, in the real world, it is often difficult to find a perfect expert and avoiding dangerous behaviors becomes relevant for safety reasons. We present the idea of \\textit{learning to avoid}, an objective opposite to imitation learning in some sense, where an agent learns to avoid a demonstrator policy given an environment. We define avoidance learning as the process of optimizing the agent's reward while avoiding dangerous behaviors given by a demonstrator. In this work we develop a framework of avoidance lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11228","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/1909.11228/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":"1909.11228","created_at":"2026-07-05T00:07:09.607128+00:00"},{"alias_kind":"arxiv_version","alias_value":"1909.11228v1","created_at":"2026-07-05T00:07:09.607128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11228","created_at":"2026-07-05T00:07:09.607128+00:00"},{"alias_kind":"pith_short_12","alias_value":"HUTQC3JZSDFX","created_at":"2026-07-05T00:07:09.607128+00:00"},{"alias_kind":"pith_short_16","alias_value":"HUTQC3JZSDFXPX6C","created_at":"2026-07-05T00:07:09.607128+00:00"},{"alias_kind":"pith_short_8","alias_value":"HUTQC3JZ","created_at":"2026-07-05T00:07:09.607128+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/HUTQC3JZSDFXPX6CEVXC3OOS3V","json":"https://pith.science/pith/HUTQC3JZSDFXPX6CEVXC3OOS3V.json","graph_json":"https://pith.science/api/pith-number/HUTQC3JZSDFXPX6CEVXC3OOS3V/graph.json","events_json":"https://pith.science/api/pith-number/HUTQC3JZSDFXPX6CEVXC3OOS3V/events.json","paper":"https://pith.science/paper/HUTQC3JZ"},"agent_actions":{"view_html":"https://pith.science/pith/HUTQC3JZSDFXPX6CEVXC3OOS3V","download_json":"https://pith.science/pith/HUTQC3JZSDFXPX6CEVXC3OOS3V.json","view_paper":"https://pith.science/paper/HUTQC3JZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1909.11228&json=true","fetch_graph":"https://pith.science/api/pith-number/HUTQC3JZSDFXPX6CEVXC3OOS3V/graph.json","fetch_events":"https://pith.science/api/pith-number/HUTQC3JZSDFXPX6CEVXC3OOS3V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HUTQC3JZSDFXPX6CEVXC3OOS3V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HUTQC3JZSDFXPX6CEVXC3OOS3V/action/storage_attestation","attest_author":"https://pith.science/pith/HUTQC3JZSDFXPX6CEVXC3OOS3V/action/author_attestation","sign_citation":"https://pith.science/pith/HUTQC3JZSDFXPX6CEVXC3OOS3V/action/citation_signature","submit_replication":"https://pith.science/pith/HUTQC3JZSDFXPX6CEVXC3OOS3V/action/replication_record"}},"created_at":"2026-07-05T00:07:09.607128+00:00","updated_at":"2026-07-05T00:07:09.607128+00:00"}