{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SO7FZDAAEQPKOOPSNZEM6HBF6P","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":"828e7c9ccf03d6a9d98fc37bd934b1fefad83b77589ba1e63f6ab81effc39ea2","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-14T21:27:10Z","title_canon_sha256":"f66bc2d3e0f985d3b40caf7b67921bb615893ff9df6cc1d15f9c7600bd9722b2"},"schema_version":"1.0","source":{"id":"2302.07351","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.07351","created_at":"2026-07-05T06:23:01Z"},{"alias_kind":"arxiv_version","alias_value":"2302.07351v2","created_at":"2026-07-05T06:23:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.07351","created_at":"2026-07-05T06:23:01Z"},{"alias_kind":"pith_short_12","alias_value":"SO7FZDAAEQPK","created_at":"2026-07-05T06:23:01Z"},{"alias_kind":"pith_short_16","alias_value":"SO7FZDAAEQPKOOPS","created_at":"2026-07-05T06:23:01Z"},{"alias_kind":"pith_short_8","alias_value":"SO7FZDAA","created_at":"2026-07-05T06:23:01Z"}],"graph_snapshots":[{"event_id":"sha256:61cf0293b5273a3159e1669c3b4383e1e67d75a376277ba10da11d0556168a00","target":"graph","created_at":"2026-07-05T06:23:01Z","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/2302.07351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe reinforcement learning (RL) trains a constraint satisfaction policy by interacting with the environment. We aim to tackle a more challenging problem: learning a safe policy from an offline dataset. We study the offline safe RL problem from a novel multi-objective optimization perspective and propose the $\\epsilon$-reducible concept to characterize problem difficulties. The inherent trade-offs between safety and task performance inspire us to propose the constrained decision transformer (CDT) approach, which can dynamically adjust the trade-offs during deployment. Extensive experiments sho","authors_text":"Ding Zhao, Tingnan Zhang, Wenhao Yu, Yihang Yao, Zhepeng Cen, Zijian Guo, Zuxin Liu","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-14T21:27:10Z","title":"Constrained Decision Transformer for Offline Safe Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.07351","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":"sha256:6f0258e78293a83f009165b8d9b82a1a85f91ff2eaf75b9e9ead6451b33d7091","target":"record","created_at":"2026-07-05T06:23:01Z","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":"828e7c9ccf03d6a9d98fc37bd934b1fefad83b77589ba1e63f6ab81effc39ea2","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-14T21:27:10Z","title_canon_sha256":"f66bc2d3e0f985d3b40caf7b67921bb615893ff9df6cc1d15f9c7600bd9722b2"},"schema_version":"1.0","source":{"id":"2302.07351","kind":"arxiv","version":2}},"canonical_sha256":"93be5c8c00241ea739f26e48cf1c25f3c29f02e0ce17232560ac10bd8f4df7da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93be5c8c00241ea739f26e48cf1c25f3c29f02e0ce17232560ac10bd8f4df7da","first_computed_at":"2026-07-05T06:23:01.837094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:01.837094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5s0BB3ELNrQblVMrGqaHNZFVmVO6qUGHz6tJRkYVR9/NjCAmxc4aAbp5ldXpTwecuX6jN3PRMTafd/G0vszMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:01.837500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.07351","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f0258e78293a83f009165b8d9b82a1a85f91ff2eaf75b9e9ead6451b33d7091","sha256:61cf0293b5273a3159e1669c3b4383e1e67d75a376277ba10da11d0556168a00"],"state_sha256":"2b80ba3f61e910e93ffa42acaeb723f8510702576ddb38c738b209004e1be0d3"}