{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YOUXTHHEJ72NQ7S4FLQ7EGA33Z","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":"1875a140d1ebf49f3c3ee82cd15d02449aff3f750e4fa078cbcdbfb0d71a418a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T22:40:07Z","title_canon_sha256":"2e7755388a1c3fbdc166926bb789eeca5ac4dbe03b5b770bfd9fbe9e9d7a6d1d"},"schema_version":"1.0","source":{"id":"1805.08313","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.08313","created_at":"2026-05-18T00:00:13Z"},{"alias_kind":"arxiv_version","alias_value":"1805.08313v2","created_at":"2026-05-18T00:00:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.08313","created_at":"2026-05-18T00:00:13Z"},{"alias_kind":"pith_short_12","alias_value":"YOUXTHHEJ72N","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YOUXTHHEJ72NQ7S4","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YOUXTHHE","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:e6116811e889b1bc72f41038c0363b312b11557f3bed0af1e7896eca01aa0658","target":"graph","created_at":"2026-05-18T00:00:13Z","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":"We propose a framework for ensuring safe behavior of a reinforcement learning agent when the reward function may be difficult to specify. In order to do this, we rely on the existence of demonstrations from expert policies, and we provide a theoretical framework for the agent to optimize in the space of rewards consistent with its existing knowledge. We propose two methods to solve the resulting optimization: an exact ellipsoid-based method and a method in the spirit of the \"follow-the-perturbed-leader\" algorithm. Our experiments demonstrate the behavior of our algorithm in both discrete and c","authors_text":"Doina Precup, Fa Wu, Jessie Huang, Yang Cai","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T22:40:07Z","title":"Learning Safe Policies with Expert Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.08313","kind":"arxiv","version":2},"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":"sha256:734858d78a1cb16ca46ba6b9809680bc447372737330256a27f7787886e46d97","target":"record","created_at":"2026-05-18T00:00:13Z","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":"1875a140d1ebf49f3c3ee82cd15d02449aff3f750e4fa078cbcdbfb0d71a418a","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-21T22:40:07Z","title_canon_sha256":"2e7755388a1c3fbdc166926bb789eeca5ac4dbe03b5b770bfd9fbe9e9d7a6d1d"},"schema_version":"1.0","source":{"id":"1805.08313","kind":"arxiv","version":2}},"canonical_sha256":"c3a9799ce44ff4d87e5c2ae1f2181bde6770a205d6e2150766e9d859c880eb61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3a9799ce44ff4d87e5c2ae1f2181bde6770a205d6e2150766e9d859c880eb61","first_computed_at":"2026-05-18T00:00:13.168474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:13.168474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dKs1/McCf3Rw6VhnHAUxHhdbNkTiUk7grTxXGljWUQgmmfe6OG0bNc79EG5eQiQiw9UvCG8G1K261Noq14tHCg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:13.169104Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.08313","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:734858d78a1cb16ca46ba6b9809680bc447372737330256a27f7787886e46d97","sha256:e6116811e889b1bc72f41038c0363b312b11557f3bed0af1e7896eca01aa0658"],"state_sha256":"e30e4d1c5cf22000c683d85a92cf4c80bd42aaeb58fca5db433e818e6b60f1b5"}