{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:32XSTSFFG2KZ2V4L56SNYDXYKA","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":"3c86200269d440a0f166f5501bd951c3ae3b934b92c4dff7126024424498d9d9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-19T21:58:42Z","title_canon_sha256":"cff795dfd0271d8698a2416624e0d0edfa8c6cbfae54c0252442d5a540efa278"},"schema_version":"1.0","source":{"id":"2006.11419","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.11419","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"arxiv_version","alias_value":"2006.11419v4","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11419","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"pith_short_12","alias_value":"32XSTSFFG2KZ","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"pith_short_16","alias_value":"32XSTSFFG2KZ2V4L","created_at":"2026-07-05T02:37:55Z"},{"alias_kind":"pith_short_8","alias_value":"32XSTSFF","created_at":"2026-07-05T02:37:55Z"}],"graph_snapshots":[{"event_id":"sha256:c8c6adf2d1b0c528e952b50b2b148aad861e253cefe30d37e2e591255e795cf5","target":"graph","created_at":"2026-07-05T02:37:55Z","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/2006.11419/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates reinforcement learning with constraints, which are indispensable in safety-critical environments. To drive the constraint violation monotonically decrease, we take the constraints as Lyapunov functions and impose new linear constraints on the policy parameters' updating dynamics. As a result, the original safety set can be forward-invariant. However, because the new guaranteed-feasible constraints are imposed on the updating dynamics instead of the original policy parameters, classic optimization algorithms are no longer applicable. To address this, we propose to learn ","authors_text":"Chuangchuang Sun, Dong-Ki Kim, Jonathan P. How","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-19T21:58:42Z","title":"FISAR: Forward Invariant Safe Reinforcement Learning with a Deep Neural Network-Based Optimize"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11419","kind":"arxiv","version":4},"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:e63784e7aa1ded6372901f779e661c95e72242a840172a260221d43382916095","target":"record","created_at":"2026-07-05T02:37:55Z","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":"3c86200269d440a0f166f5501bd951c3ae3b934b92c4dff7126024424498d9d9","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-19T21:58:42Z","title_canon_sha256":"cff795dfd0271d8698a2416624e0d0edfa8c6cbfae54c0252442d5a540efa278"},"schema_version":"1.0","source":{"id":"2006.11419","kind":"arxiv","version":4}},"canonical_sha256":"deaf29c8a536959d578befa4dc0ef8503e9da4091e32b32a8313b179d88f1d6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"deaf29c8a536959d578befa4dc0ef8503e9da4091e32b32a8313b179d88f1d6a","first_computed_at":"2026-07-05T02:37:55.628469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:37:55.628469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7lkVb8NgCmGXqTe93WlvsEZKHDaEcepJLug1PAEKJcE5sBm5bAQiODA76NBD3tRRqc4Mx7dT23tcQonTUM/uBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:37:55.628874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.11419","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e63784e7aa1ded6372901f779e661c95e72242a840172a260221d43382916095","sha256:c8c6adf2d1b0c528e952b50b2b148aad861e253cefe30d37e2e591255e795cf5"],"state_sha256":"8b78bb13f13aafb8b9cd1e7cc7ba3d61bec33df74bb43d43cce82af85a79828f"}