{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KZ3SOVG22RDHT2EBBKIE4CYMBK","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":"ce1150e08ad481b355ab5f168a0361ae57277470650ae0a4bfbbe9c5297520e1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T23:14:58Z","title_canon_sha256":"56f65fa1946d192a1ef3f1220d030c1aa5f899b98cd5e62a4305046a18718b12"},"schema_version":"1.0","source":{"id":"1901.10031","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1901.10031","created_at":"2026-05-17T23:54:15Z"},{"alias_kind":"arxiv_version","alias_value":"1901.10031v2","created_at":"2026-05-17T23:54:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10031","created_at":"2026-05-17T23:54:15Z"},{"alias_kind":"pith_short_12","alias_value":"KZ3SOVG22RDH","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KZ3SOVG22RDHT2EB","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KZ3SOVG2","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:893f56886d98ba0d89456096c4f11058d2a466b678129904db41d39f82dd6b45","target":"graph","created_at":"2026-05-17T23:54:15Z","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 study continuous action reinforcement learning problems in which it is crucial that the agent interacts with the environment only through safe policies, i.e.,~policies that do not take the agent to undesirable situations. We formulate these problems as constrained Markov decision processes (CMDPs) and present safe policy optimization algorithms that are based on a Lyapunov approach to solve them. Our algorithms can use any standard policy gradient (PG) method, such as deep deterministic policy gradient (DDPG) or proximal policy optimization (PPO), to train a neural network policy, while gua","authors_text":"Aleksandra Faust, Edgar Duenez-Guzman, Mohammad Ghavamzadeh, Ofir Nachum, Yinlam Chow","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T23:14:58Z","title":"Lyapunov-based Safe Policy Optimization for Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10031","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":"sha256:6f4a7daf7af4db4525df1a68712d3e3824da6d53cdc317e08200d38b705a0a21","target":"record","created_at":"2026-05-17T23:54:15Z","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":"ce1150e08ad481b355ab5f168a0361ae57277470650ae0a4bfbbe9c5297520e1","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-01-28T23:14:58Z","title_canon_sha256":"56f65fa1946d192a1ef3f1220d030c1aa5f899b98cd5e62a4305046a18718b12"},"schema_version":"1.0","source":{"id":"1901.10031","kind":"arxiv","version":2}},"canonical_sha256":"56772754dad44679e8810a904e0b0c0aadf2bd59b42d4d86e11144b6c4b8b1fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"56772754dad44679e8810a904e0b0c0aadf2bd59b42d4d86e11144b6c4b8b1fd","first_computed_at":"2026-05-17T23:54:15.112763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:54:15.112763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sGQQSbRKABJpAQyF/Mh8DRwkTDY3Wz0KTXG22SvbO+hGggvm64al9Fzx6TKxEqCOBdngXWNuVAuZ06QCgC+yAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:54:15.113731Z","signed_message":"canonical_sha256_bytes"},"source_id":"1901.10031","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f4a7daf7af4db4525df1a68712d3e3824da6d53cdc317e08200d38b705a0a21","sha256:893f56886d98ba0d89456096c4f11058d2a466b678129904db41d39f82dd6b45"],"state_sha256":"dded4a4caab86df2c3723ff1a1a109e26fa22fef2f0351c9597c41c1b9b2ba1d"}