{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:UFTTKZ4GK7L3BZGJMUGAB6RJHT","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":"3980100c08ca7e0e70c8584247c5737a4c3beb56ad498ed4c3e9e051497ab98d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T17:39:02Z","title_canon_sha256":"7fdaf1e06ce39accaa5805bca317d0d2950aa9e8f2ed33b044a66213317ebcc3"},"schema_version":"1.0","source":{"id":"2310.03718","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.03718","created_at":"2026-07-05T08:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2310.03718v2","created_at":"2026-07-05T08:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03718","created_at":"2026-07-05T08:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"UFTTKZ4GK7L3","created_at":"2026-07-05T08:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"UFTTKZ4GK7L3BZGJ","created_at":"2026-07-05T08:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"UFTTKZ4G","created_at":"2026-07-05T08:13:27Z"}],"graph_snapshots":[{"event_id":"sha256:213a0eb750ca7877c0a44360dbd955fa4a2bca54f6df0f8ad02f62f411dff64b","target":"graph","created_at":"2026-07-05T08:13:27Z","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/2310.03718/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning (RL) focuses on training reward-maximizing agents subject to pre-defined safety constraints. Yet, learning versatile safe policies that can adapt to varying safety constraint requirements during deployment without retraining remains a largely unexplored and challenging area. In this work, we formulate the versatile safe RL problem and consider two primary requirements: training efficiency and zero-shot adaptation capability. To address them, we introduce the Conditioned Constrained Policy Optimization (CCPO) framework, consisting of two key modules: (1) Versatile Va","authors_text":"Ding Zhao, Jiacheng Zhu, Tingnan Zhang, Wenhao Yu, Yihang Yao, Zhepeng Cen, Zuxin Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T17:39:02Z","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03718","kind":"arxiv","version":2},"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:f03c2a2f2f5ae76f0bc6e65f8e081142716fe971c3dcc340b1b0f0b4709f196a","target":"record","created_at":"2026-07-05T08:13:27Z","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":"3980100c08ca7e0e70c8584247c5737a4c3beb56ad498ed4c3e9e051497ab98d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T17:39:02Z","title_canon_sha256":"7fdaf1e06ce39accaa5805bca317d0d2950aa9e8f2ed33b044a66213317ebcc3"},"schema_version":"1.0","source":{"id":"2310.03718","kind":"arxiv","version":2}},"canonical_sha256":"a16735678657d7b0e4c9650c00fa293ceec8b9f6f68ca8d9dbd74ad91df9a816","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a16735678657d7b0e4c9650c00fa293ceec8b9f6f68ca8d9dbd74ad91df9a816","first_computed_at":"2026-07-05T08:13:27.360094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:27.360094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2fpkw+ntVqNr+d072VJX3/BtcqpJUTXHK5FUxHuE5IjZKlxVJSJy0gkdWhPZpVGpanlW8HqU9wm6XKKzhISnBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:27.360633Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.03718","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f03c2a2f2f5ae76f0bc6e65f8e081142716fe971c3dcc340b1b0f0b4709f196a","sha256:213a0eb750ca7877c0a44360dbd955fa4a2bca54f6df0f8ad02f62f411dff64b"],"state_sha256":"de1ca81833cf95f16cfb8634ee478a1098e5438a3fb3861c00a2054b00936ffd"}