{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TISCUSJNHGARPFNMVEHAIDSDWF","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":"1bd77fb38515b3332db9dbbd50e02d97b05b0ecb3778f638433a42108cd27738","cross_cats_sorted":["cs.RO","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T23:45:29Z","title_canon_sha256":"e5a80e43fd063adc3cce0c3f24f9a9a6e6be9377a3d5b91b5d19343792fda561"},"schema_version":"1.0","source":{"id":"2410.22600","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22600","created_at":"2026-07-05T09:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22600v1","created_at":"2026-07-05T09:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22600","created_at":"2026-07-05T09:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"TISCUSJNHGAR","created_at":"2026-07-05T09:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"TISCUSJNHGARPFNM","created_at":"2026-07-05T09:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"TISCUSJN","created_at":"2026-07-05T09:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:72bdc7bfa7f4e529ebc26b2a873a9b5c9fe83d9cef5f3b999832ab49c066c81f","target":"graph","created_at":"2026-07-05T09:28:19Z","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/2410.22600/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current reinforcement-learning methods are unable to directly learn policies that solve the minimum cost reach-avoid problem to minimize cumulative costs subject to the constraints of reaching the goal and avoiding unsafe states, as the structure of this new optimization problem is incompatible with current methods. Instead, a surrogate problem is solved where all objectives are combined with a weighted sum. However, this surrogate objective results in suboptimal policies that do not directly minimize the cumulative cost. In this work, we propose RC-PPO, a reinforcement-learning-based method f","authors_text":"Cheng Ge, Chuchu Fan, Oswin So","cross_cats":["cs.RO","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T23:45:29Z","title":"Solving Minimum-Cost Reach Avoid using Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22600","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":"sha256:27a510dc784b2621b53da4023be1b427579d74de00085e8c04c83eb26fa824ba","target":"record","created_at":"2026-07-05T09:28:19Z","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":"1bd77fb38515b3332db9dbbd50e02d97b05b0ecb3778f638433a42108cd27738","cross_cats_sorted":["cs.RO","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-29T23:45:29Z","title_canon_sha256":"e5a80e43fd063adc3cce0c3f24f9a9a6e6be9377a3d5b91b5d19343792fda561"},"schema_version":"1.0","source":{"id":"2410.22600","kind":"arxiv","version":1}},"canonical_sha256":"9a242a492d39811795aca90e040e43b149ed0c3cfc412e4f73ba2f524d3f19ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a242a492d39811795aca90e040e43b149ed0c3cfc412e4f73ba2f524d3f19ac","first_computed_at":"2026-07-05T09:28:19.057494Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:19.057494Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UTmZVNTXze1nCySEEGCz+dXUT51JfkVO1tY5ZAmkBHtlSDQ89PuVUlYft316Yy1hNKZmtHgZGPI7HTCCPEEWBA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:19.057980Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22600","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27a510dc784b2621b53da4023be1b427579d74de00085e8c04c83eb26fa824ba","sha256:72bdc7bfa7f4e529ebc26b2a873a9b5c9fe83d9cef5f3b999832ab49c066c81f"],"state_sha256":"e8f9a64e2a718081f79f9035bca92637ed2f0f4ec2018614c5ed1a2f3e4c7c10"}