{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:32XSTSFFG2KZ2V4L56SNYDXYKA","short_pith_number":"pith:32XSTSFF","schema_version":"1.0","canonical_sha256":"deaf29c8a536959d578befa4dc0ef8503e9da4091e32b32a8313b179d88f1d6a","source":{"kind":"arxiv","id":"2006.11419","version":4},"attestation_state":"computed","paper":{"title":"FISAR: Forward Invariant Safe Reinforcement Learning with a Deep Neural Network-Based Optimize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuangchuang Sun, Dong-Ki Kim, Jonathan P. How","submitted_at":"2020-06-19T21:58:42Z","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are imposed on the updating dynamics instead of the original policy parameters, classic optimization algorithms are no longer applicable.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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2006.11419","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-19T21:58:42Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cff795dfd0271d8698a2416624e0d0edfa8c6cbfae54c0252442d5a540efa278","abstract_canon_sha256":"3c86200269d440a0f166f5501bd951c3ae3b934b92c4dff7126024424498d9d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:37:55.628874Z","signature_b64":"7lkVb8NgCmGXqTe93WlvsEZKHDaEcepJLug1PAEKJcE5sBm5bAQiODA76NBD3tRRqc4Mx7dT23tcQonTUM/uBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"deaf29c8a536959d578befa4dc0ef8503e9da4091e32b32a8313b179d88f1d6a","last_reissued_at":"2026-07-05T02:37:55.628469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:37:55.628469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FISAR: Forward Invariant Safe Reinforcement Learning with a Deep Neural Network-Based Optimize","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chuangchuang Sun, Dong-Ki Kim, Jonathan P. How","submitted_at":"2020-06-19T21:58:42Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11419","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2006.11419/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2006.11419","created_at":"2026-07-05T02:37:55.628529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11419v4","created_at":"2026-07-05T02:37:55.628529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11419","created_at":"2026-07-05T02:37:55.628529+00:00"},{"alias_kind":"pith_short_12","alias_value":"32XSTSFFG2KZ","created_at":"2026-07-05T02:37:55.628529+00:00"},{"alias_kind":"pith_short_16","alias_value":"32XSTSFFG2KZ2V4L","created_at":"2026-07-05T02:37:55.628529+00:00"},{"alias_kind":"pith_short_8","alias_value":"32XSTSFF","created_at":"2026-07-05T02:37:55.628529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32XSTSFFG2KZ2V4L56SNYDXYKA","json":"https://pith.science/pith/32XSTSFFG2KZ2V4L56SNYDXYKA.json","graph_json":"https://pith.science/api/pith-number/32XSTSFFG2KZ2V4L56SNYDXYKA/graph.json","events_json":"https://pith.science/api/pith-number/32XSTSFFG2KZ2V4L56SNYDXYKA/events.json","paper":"https://pith.science/paper/32XSTSFF"},"agent_actions":{"view_html":"https://pith.science/pith/32XSTSFFG2KZ2V4L56SNYDXYKA","download_json":"https://pith.science/pith/32XSTSFFG2KZ2V4L56SNYDXYKA.json","view_paper":"https://pith.science/paper/32XSTSFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11419&json=true","fetch_graph":"https://pith.science/api/pith-number/32XSTSFFG2KZ2V4L56SNYDXYKA/graph.json","fetch_events":"https://pith.science/api/pith-number/32XSTSFFG2KZ2V4L56SNYDXYKA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32XSTSFFG2KZ2V4L56SNYDXYKA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32XSTSFFG2KZ2V4L56SNYDXYKA/action/storage_attestation","attest_author":"https://pith.science/pith/32XSTSFFG2KZ2V4L56SNYDXYKA/action/author_attestation","sign_citation":"https://pith.science/pith/32XSTSFFG2KZ2V4L56SNYDXYKA/action/citation_signature","submit_replication":"https://pith.science/pith/32XSTSFFG2KZ2V4L56SNYDXYKA/action/replication_record"}},"created_at":"2026-07-05T02:37:55.628529+00:00","updated_at":"2026-07-05T02:37:55.628529+00:00"}