{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:GOEFOO3W26N2E33DWGIIWWTNSE","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":"2587583faa85e16aab1ecd4ae31569dca7f4dd9ea97ab8a48cebdab3c5135327","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T04:24:09Z","title_canon_sha256":"3093f4daafd0dcb92aaea5cc82e3f41dfad172cb4eeac9b84995790f66475d86"},"schema_version":"1.0","source":{"id":"2201.11927","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.11927","created_at":"2026-07-05T04:32:38Z"},{"alias_kind":"arxiv_version","alias_value":"2201.11927v3","created_at":"2026-07-05T04:32:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.11927","created_at":"2026-07-05T04:32:38Z"},{"alias_kind":"pith_short_12","alias_value":"GOEFOO3W26N2","created_at":"2026-07-05T04:32:38Z"},{"alias_kind":"pith_short_16","alias_value":"GOEFOO3W26N2E33D","created_at":"2026-07-05T04:32:38Z"},{"alias_kind":"pith_short_8","alias_value":"GOEFOO3W","created_at":"2026-07-05T04:32:38Z"}],"graph_snapshots":[{"event_id":"sha256:9bf0ea9bbf41e6367f4e67992db8b9209418bebe8a203ab72cb7c7064177bc3d","target":"graph","created_at":"2026-07-05T04:32:38Z","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/2201.11927/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications. Previous primal-dual style approaches suffer from instability issues and lack optimality guarantees. This paper overcomes the issues from the perspective of probabilistic inference. We introduce a novel Expectation-Maximization approach to naturally incorporate constraints during the policy learning: 1) a provable optimal non-parametric variational distribution could be computed in closed form after a convex optimization (E-step); 2) the policy paramet","authors_text":"Bo Li, Ding Zhao, Vladislav Isenbaev, Wei Liu, Zhepeng Cen, Zhiwei Steven Wu, Zuxin Liu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T04:24:09Z","title":"Constrained Variational Policy Optimization for Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.11927","kind":"arxiv","version":3},"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":"sha256:4a90cb049792031949388d1d1a54e21677530efcf842a644601db6df65162977","target":"record","created_at":"2026-07-05T04:32:38Z","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":"2587583faa85e16aab1ecd4ae31569dca7f4dd9ea97ab8a48cebdab3c5135327","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-28T04:24:09Z","title_canon_sha256":"3093f4daafd0dcb92aaea5cc82e3f41dfad172cb4eeac9b84995790f66475d86"},"schema_version":"1.0","source":{"id":"2201.11927","kind":"arxiv","version":3}},"canonical_sha256":"3388573b76d79ba26f63b1908b5a6d912eceecc5002459ed908ccbb063a37d05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3388573b76d79ba26f63b1908b5a6d912eceecc5002459ed908ccbb063a37d05","first_computed_at":"2026-07-05T04:32:38.829834Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:38.829834Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uHyZ2ulIy0bd6iyPqUHI6bvMRAq0qwE7vWcbXsza5a+GKTqFM5oxufzVMoz8m/vZTWWtdFq28sjNHM30NKiuAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:38.830281Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.11927","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a90cb049792031949388d1d1a54e21677530efcf842a644601db6df65162977","sha256:9bf0ea9bbf41e6367f4e67992db8b9209418bebe8a203ab72cb7c7064177bc3d"],"state_sha256":"17e61a1bfe2e0fb755b3575cb18fb4cfebbe79600e7a51ab2d64fc9cab7a5dff"}