{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QDTAKE7R2GV4AWLMG7FJZNI34C","short_pith_number":"pith:QDTAKE7R","schema_version":"1.0","canonical_sha256":"80e60513f1d1abc0596c37ca9cb51be089cb87c19751f9c010613f48db6b405d","source":{"kind":"arxiv","id":"2303.14265","version":1},"attestation_state":"computed","paper":{"title":"Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Hongyi Chen","submitted_at":"2023-03-24T20:29:17Z","abstract_excerpt":"This study proposes a safe and sample-efficient reinforcement learning (RL) framework to address two major challenges in developing applicable RL algorithms: satisfying safety constraints and efficiently learning with limited samples. To guarantee safety in real-world complex environments, we use the safe set algorithm (SSA) to monitor and modify the nominal controls, and evaluate SSA+RL in a clustered dynamic environment which is challenging to be solved by existing RL algorithms. However, the SSA+RL framework is usually not sample-efficient especially in reward-sparse environments, which has"},"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":"2303.14265","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-24T20:29:17Z","cross_cats_sorted":["cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"37293b501e6290a4405626f6a12a5d95603f76a343efce9a8aff761dc5ef01d9","abstract_canon_sha256":"86e012574ffa98b1da6c408f5a5cb58346e4d4fbaf09f459fc48ec88e4ce4026"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:38.809005Z","signature_b64":"YOi88ot5xKUGOxnTZTfaG0PApmo58EFnUvft7OScDrUbXr1+EpB0fcHHou2ko7tx3V7e8EbLUzbvhy/uIWenDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80e60513f1d1abc0596c37ca9cb51be089cb87c19751f9c010613f48db6b405d","last_reissued_at":"2026-07-05T05:54:38.808657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:38.808657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Changliu Liu, Hongyi Chen","submitted_at":"2023-03-24T20:29:17Z","abstract_excerpt":"This study proposes a safe and sample-efficient reinforcement learning (RL) framework to address two major challenges in developing applicable RL algorithms: satisfying safety constraints and efficiently learning with limited samples. To guarantee safety in real-world complex environments, we use the safe set algorithm (SSA) to monitor and modify the nominal controls, and evaluate SSA+RL in a clustered dynamic environment which is challenging to be solved by existing RL algorithms. However, the SSA+RL framework is usually not sample-efficient especially in reward-sparse environments, which has"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14265","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/2303.14265/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":"2303.14265","created_at":"2026-07-05T05:54:38.808719+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14265v1","created_at":"2026-07-05T05:54:38.808719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14265","created_at":"2026-07-05T05:54:38.808719+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDTAKE7R2GV4","created_at":"2026-07-05T05:54:38.808719+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDTAKE7R2GV4AWLM","created_at":"2026-07-05T05:54:38.808719+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDTAKE7R","created_at":"2026-07-05T05:54:38.808719+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/QDTAKE7R2GV4AWLMG7FJZNI34C","json":"https://pith.science/pith/QDTAKE7R2GV4AWLMG7FJZNI34C.json","graph_json":"https://pith.science/api/pith-number/QDTAKE7R2GV4AWLMG7FJZNI34C/graph.json","events_json":"https://pith.science/api/pith-number/QDTAKE7R2GV4AWLMG7FJZNI34C/events.json","paper":"https://pith.science/paper/QDTAKE7R"},"agent_actions":{"view_html":"https://pith.science/pith/QDTAKE7R2GV4AWLMG7FJZNI34C","download_json":"https://pith.science/pith/QDTAKE7R2GV4AWLMG7FJZNI34C.json","view_paper":"https://pith.science/paper/QDTAKE7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14265&json=true","fetch_graph":"https://pith.science/api/pith-number/QDTAKE7R2GV4AWLMG7FJZNI34C/graph.json","fetch_events":"https://pith.science/api/pith-number/QDTAKE7R2GV4AWLMG7FJZNI34C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDTAKE7R2GV4AWLMG7FJZNI34C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDTAKE7R2GV4AWLMG7FJZNI34C/action/storage_attestation","attest_author":"https://pith.science/pith/QDTAKE7R2GV4AWLMG7FJZNI34C/action/author_attestation","sign_citation":"https://pith.science/pith/QDTAKE7R2GV4AWLMG7FJZNI34C/action/citation_signature","submit_replication":"https://pith.science/pith/QDTAKE7R2GV4AWLMG7FJZNI34C/action/replication_record"}},"created_at":"2026-07-05T05:54:38.808719+00:00","updated_at":"2026-07-05T05:54:38.808719+00:00"}