{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2M6S2JDOGQZXWYO3LNKR7CUDQN","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":"3734c4755d92e83e814dfc7fa09140d13be6e032e7d94728af1e7c3817c3bc37","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T03:11:25Z","title_canon_sha256":"87dd7aad0cd0e4d4b999ac08e49f144a470f1197600372edff3f5bbf6e28bc1a"},"schema_version":"1.0","source":{"id":"2212.06998","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.06998","created_at":"2026-07-05T05:25:19Z"},{"alias_kind":"arxiv_version","alias_value":"2212.06998v1","created_at":"2026-07-05T05:25:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.06998","created_at":"2026-07-05T05:25:19Z"},{"alias_kind":"pith_short_12","alias_value":"2M6S2JDOGQZX","created_at":"2026-07-05T05:25:19Z"},{"alias_kind":"pith_short_16","alias_value":"2M6S2JDOGQZXWYO3","created_at":"2026-07-05T05:25:19Z"},{"alias_kind":"pith_short_8","alias_value":"2M6S2JDO","created_at":"2026-07-05T05:25:19Z"}],"graph_snapshots":[{"event_id":"sha256:8e1395cff8be833efce089640593957427b3a5209cad9f20a93863146601eadb","target":"graph","created_at":"2026-07-05T05:25:19Z","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/2212.06998/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning a risk-aware policy is essential but rather challenging in unstructured robotic tasks. Safe reinforcement learning methods open up new possibilities to tackle this problem. However, the conservative policy updates make it intractable to achieve sufficient exploration and desirable performance in complex, sample-expensive environments. In this paper, we propose a dual-agent safe reinforcement learning strategy consisting of a baseline and a safe agent. Such a decoupled framework enables high flexibility, data efficiency and risk-awareness for RL-based control. Concretely, the baseline ","authors_text":"Dacheng Tao, Linrui Zhang, Li Shen, Shoujie Li, Xueqian Wang, Zichen Yan","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T03:11:25Z","title":"Safety Correction from Baseline: Towards the Risk-aware Policy in Robotics via Dual-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.06998","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":"sha256:54c9fd860cd83c6368227077d42fbec3361c90b075776f347f491df283a09033","target":"record","created_at":"2026-07-05T05:25:19Z","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":"3734c4755d92e83e814dfc7fa09140d13be6e032e7d94728af1e7c3817c3bc37","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T03:11:25Z","title_canon_sha256":"87dd7aad0cd0e4d4b999ac08e49f144a470f1197600372edff3f5bbf6e28bc1a"},"schema_version":"1.0","source":{"id":"2212.06998","kind":"arxiv","version":1}},"canonical_sha256":"d33d2d246e34337b61db5b551f8a83834cf95849b9517e23d5d18d2628182df4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d33d2d246e34337b61db5b551f8a83834cf95849b9517e23d5d18d2628182df4","first_computed_at":"2026-07-05T05:25:19.786368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:25:19.786368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a9BTf+3YkEIt0QkZSnlRlqWXEOzTA5sQFnytDwvSi87PAL7i15m20JhOyv4BkW/4eeFmh+QNN+YKrJm+RrqsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:25:19.786903Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.06998","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54c9fd860cd83c6368227077d42fbec3361c90b075776f347f491df283a09033","sha256:8e1395cff8be833efce089640593957427b3a5209cad9f20a93863146601eadb"],"state_sha256":"de60a49684ee031f059c5e6358d9faa504197922f593699b11a7e5bd08672778"}