{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MQYAMW7RYJJRXESUJH4YYP5NP3","short_pith_number":"pith:MQYAMW7R","schema_version":"1.0","canonical_sha256":"6430065bf1c2531b925449f98c3fad7ed21b97774d06b6ff3b7eaf45ee809e4b","source":{"kind":"arxiv","id":"2312.15127","version":1},"attestation_state":"computed","paper":{"title":"Gradient Shaping for Multi-Constraint Safe Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Peide Huang, Tingnan Zhang, Wenhao Yu, Yihang Yao, Zhepeng Cen, Zuxin Liu","submitted_at":"2023-12-23T00:55:09Z","abstract_excerpt":"Online safe reinforcement learning (RL) involves training a policy that maximizes task efficiency while satisfying constraints via interacting with the environments. In this paper, our focus lies in addressing the complex challenges associated with solving multi-constraint (MC) safe RL problems. We approach the safe RL problem from the perspective of Multi-Objective Optimization (MOO) and propose a unified framework designed for MC safe RL algorithms. This framework highlights the manipulation of gradients derived from constraints. Leveraging insights from this framework and recognizing the si"},"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":"2312.15127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-23T00:55:09Z","cross_cats_sorted":[],"title_canon_sha256":"c17f784558e6a068873247c1a28084b492feaa72f081d274ab7bb4cb7e68d049","abstract_canon_sha256":"8620dcef6393a0f8882318a1788e1a52e6d7ca6015f38229040d55cd208a8052"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:31.202326Z","signature_b64":"QSKZyZKsGt5eH1YRtwSTYcawfBVrJhNzfQ2QK1IZJj6rgSfy30n9HqI4TTTZichOY+NGZDq00wh7XDFvPrJFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6430065bf1c2531b925449f98c3fad7ed21b97774d06b6ff3b7eaf45ee809e4b","last_reissued_at":"2026-07-05T07:27:31.201905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:31.201905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradient Shaping for Multi-Constraint Safe Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ding Zhao, Peide Huang, Tingnan Zhang, Wenhao Yu, Yihang Yao, Zhepeng Cen, Zuxin Liu","submitted_at":"2023-12-23T00:55:09Z","abstract_excerpt":"Online safe reinforcement learning (RL) involves training a policy that maximizes task efficiency while satisfying constraints via interacting with the environments. In this paper, our focus lies in addressing the complex challenges associated with solving multi-constraint (MC) safe RL problems. We approach the safe RL problem from the perspective of Multi-Objective Optimization (MOO) and propose a unified framework designed for MC safe RL algorithms. This framework highlights the manipulation of gradients derived from constraints. Leveraging insights from this framework and recognizing the si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15127","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/2312.15127/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":"2312.15127","created_at":"2026-07-05T07:27:31.201965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.15127v1","created_at":"2026-07-05T07:27:31.201965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15127","created_at":"2026-07-05T07:27:31.201965+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQYAMW7RYJJR","created_at":"2026-07-05T07:27:31.201965+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQYAMW7RYJJRXESU","created_at":"2026-07-05T07:27:31.201965+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQYAMW7R","created_at":"2026-07-05T07:27:31.201965+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/MQYAMW7RYJJRXESUJH4YYP5NP3","json":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3.json","graph_json":"https://pith.science/api/pith-number/MQYAMW7RYJJRXESUJH4YYP5NP3/graph.json","events_json":"https://pith.science/api/pith-number/MQYAMW7RYJJRXESUJH4YYP5NP3/events.json","paper":"https://pith.science/paper/MQYAMW7R"},"agent_actions":{"view_html":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3","download_json":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3.json","view_paper":"https://pith.science/paper/MQYAMW7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.15127&json=true","fetch_graph":"https://pith.science/api/pith-number/MQYAMW7RYJJRXESUJH4YYP5NP3/graph.json","fetch_events":"https://pith.science/api/pith-number/MQYAMW7RYJJRXESUJH4YYP5NP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/action/storage_attestation","attest_author":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/action/author_attestation","sign_citation":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/action/citation_signature","submit_replication":"https://pith.science/pith/MQYAMW7RYJJRXESUJH4YYP5NP3/action/replication_record"}},"created_at":"2026-07-05T07:27:31.201965+00:00","updated_at":"2026-07-05T07:27:31.201965+00:00"}