{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FOE2SUE2QJ4V4OPEY7HJOA3YSY","short_pith_number":"pith:FOE2SUE2","schema_version":"1.0","canonical_sha256":"2b89a9509a82795e39e4c7ce9703789609e7ab39eb88bc1cdc51e63e3a8185fe","source":{"kind":"arxiv","id":"2502.10431","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Constraint Violation Signals For Action-Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akshat Kumar, Janaka Chathuranga Brahmanage, Jiajing Ling","submitted_at":"2025-02-08T12:58:26Z","abstract_excerpt":"In many RL applications, ensuring an agent's actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues like the zero gradient problem and higher runtime due to the usage of optimization solvers. Recently methods were proposed to train generative models to learn a differentiable mapping between latent variables and feasible actions to address this issue. However, generative models require training using"},"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":"2502.10431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-08T12:58:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7b0749f2af82ee7793a6bc03e88fc1ddab491833890b7fb1769a4503dce1c7db","abstract_canon_sha256":"1198b775d9c18a9623128bef53464ffa3d29b6ee02d9bb09ce8bff6e3e4d1ad1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:52.504898Z","signature_b64":"cRGWVgqUqft2k5eR2JWI4lkRo97XD8xlYCmxVTj4krTKM4TY8nnGWxMAgY4CHR/RqccmXu5o1zs4aOxNXDuzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b89a9509a82795e39e4c7ce9703789609e7ab39eb88bc1cdc51e63e3a8185fe","last_reissued_at":"2026-07-05T10:14:52.504405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:52.504405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Constraint Violation Signals For Action-Constrained Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Akshat Kumar, Janaka Chathuranga Brahmanage, Jiajing Ling","submitted_at":"2025-02-08T12:58:26Z","abstract_excerpt":"In many RL applications, ensuring an agent's actions adhere to constraints is crucial for safety. Most previous methods in Action-Constrained Reinforcement Learning (ACRL) employ a projection layer after the policy network to correct the action. However projection-based methods suffer from issues like the zero gradient problem and higher runtime due to the usage of optimization solvers. Recently methods were proposed to train generative models to learn a differentiable mapping between latent variables and feasible actions to address this issue. However, generative models require training using"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.10431","kind":"arxiv","version":1},"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/2502.10431/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":"2502.10431","created_at":"2026-07-05T10:14:52.504462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.10431v1","created_at":"2026-07-05T10:14:52.504462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.10431","created_at":"2026-07-05T10:14:52.504462+00:00"},{"alias_kind":"pith_short_12","alias_value":"FOE2SUE2QJ4V","created_at":"2026-07-05T10:14:52.504462+00:00"},{"alias_kind":"pith_short_16","alias_value":"FOE2SUE2QJ4V4OPE","created_at":"2026-07-05T10:14:52.504462+00:00"},{"alias_kind":"pith_short_8","alias_value":"FOE2SUE2","created_at":"2026-07-05T10:14:52.504462+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/FOE2SUE2QJ4V4OPEY7HJOA3YSY","json":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY.json","graph_json":"https://pith.science/api/pith-number/FOE2SUE2QJ4V4OPEY7HJOA3YSY/graph.json","events_json":"https://pith.science/api/pith-number/FOE2SUE2QJ4V4OPEY7HJOA3YSY/events.json","paper":"https://pith.science/paper/FOE2SUE2"},"agent_actions":{"view_html":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY","download_json":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY.json","view_paper":"https://pith.science/paper/FOE2SUE2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.10431&json=true","fetch_graph":"https://pith.science/api/pith-number/FOE2SUE2QJ4V4OPEY7HJOA3YSY/graph.json","fetch_events":"https://pith.science/api/pith-number/FOE2SUE2QJ4V4OPEY7HJOA3YSY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/action/storage_attestation","attest_author":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/action/author_attestation","sign_citation":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/action/citation_signature","submit_replication":"https://pith.science/pith/FOE2SUE2QJ4V4OPEY7HJOA3YSY/action/replication_record"}},"created_at":"2026-07-05T10:14:52.504462+00:00","updated_at":"2026-07-05T10:14:52.504462+00:00"}