{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HUTQC3JZSDFXPX6CEVXC3OOS3V","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":"b1ba5dc5c04678010f8be62476d9ba6dc0b17f5627584c5f263568969bc426a5","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-09-24T23:37:35Z","title_canon_sha256":"0122364b2d6e12d9a4d0867db93be92a30ee29ba7bf8090a990426b0cf962453"},"schema_version":"1.0","source":{"id":"1909.11228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11228","created_at":"2026-07-05T00:07:09Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11228v1","created_at":"2026-07-05T00:07:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11228","created_at":"2026-07-05T00:07:09Z"},{"alias_kind":"pith_short_12","alias_value":"HUTQC3JZSDFX","created_at":"2026-07-05T00:07:09Z"},{"alias_kind":"pith_short_16","alias_value":"HUTQC3JZSDFXPX6C","created_at":"2026-07-05T00:07:09Z"},{"alias_kind":"pith_short_8","alias_value":"HUTQC3JZ","created_at":"2026-07-05T00:07:09Z"}],"graph_snapshots":[{"event_id":"sha256:80a2f7e5b6fe485bd04f6236ae4b78e88eb2d8db5cb1cc1dbec28a409f3ac0d2","target":"graph","created_at":"2026-07-05T00:07:09Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.11228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"David Venuto, Doina Precup, Jhelum Chakravorty, Junhao Wang, Leonard Boussioux, Rola Dali, Yoshua Bengio","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-09-24T23:37:35Z","title":"Avoidance Learning Using Observational Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11228","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:ebd5075f910acc0ad83d68d299dae99fe6405413adeb24895a355ca877b8d68b","target":"record","created_at":"2026-07-05T00:07:09Z","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":"b1ba5dc5c04678010f8be62476d9ba6dc0b17f5627584c5f263568969bc426a5","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-09-24T23:37:35Z","title_canon_sha256":"0122364b2d6e12d9a4d0867db93be92a30ee29ba7bf8090a990426b0cf962453"},"schema_version":"1.0","source":{"id":"1909.11228","kind":"arxiv","version":1}},"canonical_sha256":"3d27016d3990cb77dfc2256e2db9d2dd4bc958065816195837aed299347ec3cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d27016d3990cb77dfc2256e2db9d2dd4bc958065816195837aed299347ec3cc","first_computed_at":"2026-07-05T00:07:09.607067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:07:09.607067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pXkYR9QAPNC+iyVlAXSgctKTNSX8JsFPoOsnNPS88GTPH3MnUCaQfuDdrUvgCq72Rndidu6f7pNWFAkYtRs6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:07:09.607609Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebd5075f910acc0ad83d68d299dae99fe6405413adeb24895a355ca877b8d68b","sha256:80a2f7e5b6fe485bd04f6236ae4b78e88eb2d8db5cb1cc1dbec28a409f3ac0d2"],"state_sha256":"ae71caa63b9f055086c3bd9ae640f7b3576051f65eb208967abbb00038210ecb"}