{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:N4AKNFEEMVKTLUS4FAVRDI26CW","short_pith_number":"pith:N4AKNFEE","schema_version":"1.0","canonical_sha256":"6f00a69484655535d25c282b11a35e158dfdf61c2a40bde7afe721b695d448bc","source":{"kind":"arxiv","id":"2302.14339","version":2},"attestation_state":"computed","paper":{"title":"Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Haotian Xu, Qing Zhuo, Shengjie Wang, Tao Zhang, Yang Gao, Yunzhe Zhang, Zhaolei Wang","submitted_at":"2023-02-28T06:16:34Z","abstract_excerpt":"Reinforcement learning (RL) has achieved promising results on most robotic control tasks. Safety of learning-based controllers is an essential notion of ensuring the effectiveness of the controllers. Current methods adopt whole consistency constraints during the training, thus resulting in inefficient exploration in the early stage. In this paper, we propose an algorithm named Constrained Policy Optimization with Extra Safety Budget (ESB-CPO) to strike a balance between the exploration efficiency and the constraints satisfaction. In the early stage, our method loosens the practical constraints"},"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":"2302.14339","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-02-28T06:16:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3e3fae018b2c18edb1e2085e2ee754d6b9de7b5bd0ae3fd4a1d950770f525d6f","abstract_canon_sha256":"3dc1574a22308c524c1919a497b88db04cf9712ba3d1c161f1b47a807f915014"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:35:26.425139Z","signature_b64":"lGPRHKaUMLIqhoFaojkK2RMmQUxoO8dmnevnAQTlbRJJ0ohUbA9JJQLDqSuyKQ/QMO3i8HvjlMeipjfRk+uxDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f00a69484655535d25c282b11a35e158dfdf61c2a40bde7afe721b695d448bc","last_reissued_at":"2026-07-05T06:35:26.424656Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:35:26.424656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Exploration Using Extra Safety Budget in Constrained Policy Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Haotian Xu, Qing Zhuo, Shengjie Wang, Tao Zhang, Yang Gao, Yunzhe Zhang, Zhaolei Wang","submitted_at":"2023-02-28T06:16:34Z","abstract_excerpt":"Reinforcement learning (RL) has achieved promising results on most robotic control tasks. Safety of learning-based controllers is an essential notion of ensuring the effectiveness of the controllers. Current methods adopt whole consistency constraints during the training, thus resulting in inefficient exploration in the early stage. In this paper, we propose an algorithm named Constrained Policy Optimization with Extra Safety Budget (ESB-CPO) to strike a balance between the exploration efficiency and the constraints satisfaction. In the early stage, our method loosens the practical constraints"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.14339","kind":"arxiv","version":2},"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/2302.14339/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":"2302.14339","created_at":"2026-07-05T06:35:26.424715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.14339v2","created_at":"2026-07-05T06:35:26.424715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.14339","created_at":"2026-07-05T06:35:26.424715+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4AKNFEEMVKT","created_at":"2026-07-05T06:35:26.424715+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4AKNFEEMVKTLUS4","created_at":"2026-07-05T06:35:26.424715+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4AKNFEE","created_at":"2026-07-05T06:35:26.424715+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/N4AKNFEEMVKTLUS4FAVRDI26CW","json":"https://pith.science/pith/N4AKNFEEMVKTLUS4FAVRDI26CW.json","graph_json":"https://pith.science/api/pith-number/N4AKNFEEMVKTLUS4FAVRDI26CW/graph.json","events_json":"https://pith.science/api/pith-number/N4AKNFEEMVKTLUS4FAVRDI26CW/events.json","paper":"https://pith.science/paper/N4AKNFEE"},"agent_actions":{"view_html":"https://pith.science/pith/N4AKNFEEMVKTLUS4FAVRDI26CW","download_json":"https://pith.science/pith/N4AKNFEEMVKTLUS4FAVRDI26CW.json","view_paper":"https://pith.science/paper/N4AKNFEE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.14339&json=true","fetch_graph":"https://pith.science/api/pith-number/N4AKNFEEMVKTLUS4FAVRDI26CW/graph.json","fetch_events":"https://pith.science/api/pith-number/N4AKNFEEMVKTLUS4FAVRDI26CW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4AKNFEEMVKTLUS4FAVRDI26CW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4AKNFEEMVKTLUS4FAVRDI26CW/action/storage_attestation","attest_author":"https://pith.science/pith/N4AKNFEEMVKTLUS4FAVRDI26CW/action/author_attestation","sign_citation":"https://pith.science/pith/N4AKNFEEMVKTLUS4FAVRDI26CW/action/citation_signature","submit_replication":"https://pith.science/pith/N4AKNFEEMVKTLUS4FAVRDI26CW/action/replication_record"}},"created_at":"2026-07-05T06:35:26.424715+00:00","updated_at":"2026-07-05T06:35:26.424715+00:00"}