{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TIB32Z2NBKMBGOV3D76TGJN3QU","short_pith_number":"pith:TIB32Z2N","schema_version":"1.0","canonical_sha256":"9a03bd674d0a98133abb1ffd3325bb8511c9ce6318a3daaf31ca0be46a6b77f1","source":{"kind":"arxiv","id":"2312.10385","version":4},"attestation_state":"computed","paper":{"title":"Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huy Hoang, Pradeep Varakantham, Tien Mai","submitted_at":"2023-12-16T08:48:46Z","abstract_excerpt":"A popular framework for enforcing safe actions in Reinforcement Learning (RL) is Constrained RL, where trajectory based constraints on expected cost (or other cost measures) are employed to enforce safety and more importantly these constraints are enforced while maximizing expected reward. Most recent approaches for solving Constrained RL convert the trajectory based cost constraint into a surrogate problem that can be solved using minor modifications to RL methods. A key drawback with such approaches is an over or underestimation of the cost constraint at each state. Therefore, we provide an "},"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":"2312.10385","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-16T08:48:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90ccd7a7ddf4ba14c28d25a8d35a6607d0925c29698080c6854d24553d2daccb","abstract_canon_sha256":"bf13ae6c6ef0f7bc150316fed4bc3892d61dc032b3cd043d50e2e0eb070eba1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:18.933837Z","signature_b64":"3kgkUHA4mmkzWgZw8+h7eZDvCMEBg2Qm0WjdaktGFhbJP3d8x8zjKoyfM2mipv+iCb4Z5lOf49txye3rJYtqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a03bd674d0a98133abb1ffd3325bb8511c9ce6318a3daaf31ca0be46a6b77f1","last_reissued_at":"2026-07-05T08:53:18.933349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:18.933349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Imitate the Good and Avoid the Bad: An Incremental Approach to Safe Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Huy Hoang, Pradeep Varakantham, Tien Mai","submitted_at":"2023-12-16T08:48:46Z","abstract_excerpt":"A popular framework for enforcing safe actions in Reinforcement Learning (RL) is Constrained RL, where trajectory based constraints on expected cost (or other cost measures) are employed to enforce safety and more importantly these constraints are enforced while maximizing expected reward. Most recent approaches for solving Constrained RL convert the trajectory based cost constraint into a surrogate problem that can be solved using minor modifications to RL methods. A key drawback with such approaches is an over or underestimation of the cost constraint at each state. Therefore, we provide an "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.10385","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/2312.10385/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":"2312.10385","created_at":"2026-07-05T08:53:18.933409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.10385v4","created_at":"2026-07-05T08:53:18.933409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.10385","created_at":"2026-07-05T08:53:18.933409+00:00"},{"alias_kind":"pith_short_12","alias_value":"TIB32Z2NBKMB","created_at":"2026-07-05T08:53:18.933409+00:00"},{"alias_kind":"pith_short_16","alias_value":"TIB32Z2NBKMBGOV3","created_at":"2026-07-05T08:53:18.933409+00:00"},{"alias_kind":"pith_short_8","alias_value":"TIB32Z2N","created_at":"2026-07-05T08:53:18.933409+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/TIB32Z2NBKMBGOV3D76TGJN3QU","json":"https://pith.science/pith/TIB32Z2NBKMBGOV3D76TGJN3QU.json","graph_json":"https://pith.science/api/pith-number/TIB32Z2NBKMBGOV3D76TGJN3QU/graph.json","events_json":"https://pith.science/api/pith-number/TIB32Z2NBKMBGOV3D76TGJN3QU/events.json","paper":"https://pith.science/paper/TIB32Z2N"},"agent_actions":{"view_html":"https://pith.science/pith/TIB32Z2NBKMBGOV3D76TGJN3QU","download_json":"https://pith.science/pith/TIB32Z2NBKMBGOV3D76TGJN3QU.json","view_paper":"https://pith.science/paper/TIB32Z2N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.10385&json=true","fetch_graph":"https://pith.science/api/pith-number/TIB32Z2NBKMBGOV3D76TGJN3QU/graph.json","fetch_events":"https://pith.science/api/pith-number/TIB32Z2NBKMBGOV3D76TGJN3QU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TIB32Z2NBKMBGOV3D76TGJN3QU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TIB32Z2NBKMBGOV3D76TGJN3QU/action/storage_attestation","attest_author":"https://pith.science/pith/TIB32Z2NBKMBGOV3D76TGJN3QU/action/author_attestation","sign_citation":"https://pith.science/pith/TIB32Z2NBKMBGOV3D76TGJN3QU/action/citation_signature","submit_replication":"https://pith.science/pith/TIB32Z2NBKMBGOV3D76TGJN3QU/action/replication_record"}},"created_at":"2026-07-05T08:53:18.933409+00:00","updated_at":"2026-07-05T08:53:18.933409+00:00"}