{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MSRMPWV2QJHBSDNS2JNWWFXA6X","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":"0bfaa7e64332a985da599d9e0d34b1e60206a52b46a688294ea2c95bdf8e61fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-10T18:01:16Z","title_canon_sha256":"0967a8ea7f9432be4dadb339a2ef64231faa1e4e2254bb4faefc3193c1999bc5"},"schema_version":"1.0","source":{"id":"2310.06903","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.06903","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"arxiv_version","alias_value":"2310.06903v2","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.06903","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"pith_short_12","alias_value":"MSRMPWV2QJHB","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"pith_short_16","alias_value":"MSRMPWV2QJHBSDNS","created_at":"2026-07-05T08:43:23Z"},{"alias_kind":"pith_short_8","alias_value":"MSRMPWV2","created_at":"2026-07-05T08:43:23Z"}],"graph_snapshots":[{"event_id":"sha256:e610703ae63609b681901ec04f45fd7b56141bbab4246a61ee6e961b756bd2a5","target":"graph","created_at":"2026-07-05T08:43:23Z","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/2310.06903/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe Reinforcement Learning (RL) plays an important role in applying RL algorithms to safety-critical real-world applications, addressing the trade-off between maximizing rewards and adhering to safety constraints. This work introduces a novel approach that combines RL with trajectory optimization to manage this trade-off effectively. Our approach embeds safety constraints within the action space of a modified Markov Decision Process (MDP). The RL agent produces a sequence of actions that are transformed into safe trajectories by a trajectory optimizer, thereby effectively ensuring safety and ","authors_text":"David Held, Ding Zhao, Fan Yang, Wenxuan Zhou, Zuxin Liu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-10T18:01:16Z","title":"Reinforcement Learning in a Safety-Embedded MDP with Trajectory Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.06903","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":"sha256:79494fe27ed929849466bd1dc3cfe4c25ddc77b906cf9cd01a09e7289d7f4b27","target":"record","created_at":"2026-07-05T08:43:23Z","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":"0bfaa7e64332a985da599d9e0d34b1e60206a52b46a688294ea2c95bdf8e61fc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-10-10T18:01:16Z","title_canon_sha256":"0967a8ea7f9432be4dadb339a2ef64231faa1e4e2254bb4faefc3193c1999bc5"},"schema_version":"1.0","source":{"id":"2310.06903","kind":"arxiv","version":2}},"canonical_sha256":"64a2c7daba824e190db2d25b6b16e0f5e724ec482c78d96cbfeb50f4f4f185c0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64a2c7daba824e190db2d25b6b16e0f5e724ec482c78d96cbfeb50f4f4f185c0","first_computed_at":"2026-07-05T08:43:23.798256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:43:23.798256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uWjN4PD7DIWCWjrntElSJt6d2Rwn3npd058UgqQrpATPQTZZ3PlSe0t1Uogty9ccnKqwe0NyC+cjPRLnBimACw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:43:23.798696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.06903","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79494fe27ed929849466bd1dc3cfe4c25ddc77b906cf9cd01a09e7289d7f4b27","sha256:e610703ae63609b681901ec04f45fd7b56141bbab4246a61ee6e961b756bd2a5"],"state_sha256":"34f830deb8bb2661a21b7547d06456c931dc5aabdb99d7bc2e3ab67615fd7a2f"}