{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FJF72XD5XDRSEWWEZ3BA2EZAEJ","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":"44e60662697f9c8fadbf52248608f7eba3b4da4472ff27ed25b1553fa24b469b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-20T17:42:38Z","title_canon_sha256":"219119a6fa9fbb14d32b77777ff56427299cde0805eeeefc3f787dafd3eeb2be"},"schema_version":"1.0","source":{"id":"2205.10330","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.10330","created_at":"2026-07-05T08:22:54Z"},{"alias_kind":"arxiv_version","alias_value":"2205.10330v5","created_at":"2026-07-05T08:22:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.10330","created_at":"2026-07-05T08:22:54Z"},{"alias_kind":"pith_short_12","alias_value":"FJF72XD5XDRS","created_at":"2026-07-05T08:22:54Z"},{"alias_kind":"pith_short_16","alias_value":"FJF72XD5XDRSEWWE","created_at":"2026-07-05T08:22:54Z"},{"alias_kind":"pith_short_8","alias_value":"FJF72XD5","created_at":"2026-07-05T08:22:54Z"}],"graph_snapshots":[{"event_id":"sha256:004c6ef85df17040cfd271f9db85bfac23f22948c76a1215814f2234c713bc63","target":"graph","created_at":"2026-07-05T08:22:54Z","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/2205.10330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) has achieved tremendous success in many complex decision-making tasks. However, safety concerns are raised during deploying RL in real-world applications, leading to a growing demand for safe RL algorithms, such as in autonomous driving and robotics scenarios. While safe control has a long history, the study of safe RL algorithms is still in the early stages. To establish a good foundation for future safe RL research, in this paper, we provide a review of safe RL from the perspectives of methods, theories, and applications. Firstly, we review the progress of safe RL","authors_text":"Alois Knoll, Florian Walter, Guang Chen, Jun Wang, Long Yang, Shangding Gu, Yali Du","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-20T17:42:38Z","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.10330","kind":"arxiv","version":5},"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":"sha256:3ef476c3138a3b585fb7823acc16bf6a76c3b4bf3acd9414b74d29073a2f3ada","target":"record","created_at":"2026-07-05T08:22:54Z","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":"44e60662697f9c8fadbf52248608f7eba3b4da4472ff27ed25b1553fa24b469b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-20T17:42:38Z","title_canon_sha256":"219119a6fa9fbb14d32b77777ff56427299cde0805eeeefc3f787dafd3eeb2be"},"schema_version":"1.0","source":{"id":"2205.10330","kind":"arxiv","version":5}},"canonical_sha256":"2a4bfd5c7db8e3225ac4cec20d13202259fb17614c07839abcba3c08890fa1e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2a4bfd5c7db8e3225ac4cec20d13202259fb17614c07839abcba3c08890fa1e7","first_computed_at":"2026-07-05T08:22:54.339648Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:22:54.339648Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oGfvb+kWKbqYsilARSdEZyWDr8O6dj/PKg67VtIPRxNFm8fpPqkgtqd50SJzZ1wPnBriuak6Sqr49seHSAs+Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:22:54.340077Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.10330","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ef476c3138a3b585fb7823acc16bf6a76c3b4bf3acd9414b74d29073a2f3ada","sha256:004c6ef85df17040cfd271f9db85bfac23f22948c76a1215814f2234c713bc63"],"state_sha256":"e548d8f05cfc21e6af531ca4626dc7f2776114d740cfc7b948528792994c09db"}