{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QDTAKE7R2GV4AWLMG7FJZNI34C","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"86e012574ffa98b1da6c408f5a5cb58346e4d4fbaf09f459fc48ec88e4ce4026","cross_cats_sorted":["cs.RO","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-24T20:29:17Z","title_canon_sha256":"37293b501e6290a4405626f6a12a5d95603f76a343efce9a8aff761dc5ef01d9"},"schema_version":"1.0","source":{"id":"2303.14265","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14265","created_at":"2026-07-05T05:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14265v1","created_at":"2026-07-05T05:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14265","created_at":"2026-07-05T05:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"QDTAKE7R2GV4","created_at":"2026-07-05T05:54:38Z"},{"alias_kind":"pith_short_16","alias_value":"QDTAKE7R2GV4AWLM","created_at":"2026-07-05T05:54:38Z"},{"alias_kind":"pith_short_8","alias_value":"QDTAKE7R","created_at":"2026-07-05T05:54:38Z"}],"graph_snapshots":[{"event_id":"sha256:0205f30dfd53ee6c32aeaddb86729f598a913a4c4d5e69c2f5e2501dc29fa285","target":"graph","created_at":"2026-07-05T05:54:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2303.14265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changliu Liu, Hongyi Chen","cross_cats":["cs.RO","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-24T20:29:17Z","title":"Safe and Sample-efficient Reinforcement Learning for Clustered Dynamic Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14265","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8dbf958cd55214d81e5c7255c9331c7e643cd4b3e6ebe752aa0051bf18297496","target":"record","created_at":"2026-07-05T05:54:38Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"86e012574ffa98b1da6c408f5a5cb58346e4d4fbaf09f459fc48ec88e4ce4026","cross_cats_sorted":["cs.RO","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-24T20:29:17Z","title_canon_sha256":"37293b501e6290a4405626f6a12a5d95603f76a343efce9a8aff761dc5ef01d9"},"schema_version":"1.0","source":{"id":"2303.14265","kind":"arxiv","version":1}},"canonical_sha256":"80e60513f1d1abc0596c37ca9cb51be089cb87c19751f9c010613f48db6b405d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80e60513f1d1abc0596c37ca9cb51be089cb87c19751f9c010613f48db6b405d","first_computed_at":"2026-07-05T05:54:38.808657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:38.808657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YOi88ot5xKUGOxnTZTfaG0PApmo58EFnUvft7OScDrUbXr1+EpB0fcHHou2ko7tx3V7e8EbLUzbvhy/uIWenDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:38.809005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14265","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8dbf958cd55214d81e5c7255c9331c7e643cd4b3e6ebe752aa0051bf18297496","sha256:0205f30dfd53ee6c32aeaddb86729f598a913a4c4d5e69c2f5e2501dc29fa285"],"state_sha256":"1f90d4b8efded3658e6f6dbbe0eb70952d97d3e8fdf4b6bf0daa5ccf55493158"}