{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LOCID7ALNBRAKYHFRNSZQEWZ7W","short_pith_number":"pith:LOCID7AL","schema_version":"1.0","canonical_sha256":"5b8481fc0b68620560e58b659812d9fdbbabd933d5e7309f787caad4efa1212a","source":{"kind":"arxiv","id":"2203.10142","version":3},"attestation_state":"computed","paper":{"title":"Infinite-Horizon Reach-Avoid Zero-Sum Games via Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Claire J. Tomlin, Donggun Lee, Jingqi Li, Somayeh Sojoudi","submitted_at":"2022-03-18T19:48:19Z","abstract_excerpt":"In this paper, we consider the infinite-horizon reach-avoid zero-sum game problem, where the goal is to find a set in the state space, referred to as the reach-avoid set, such that the system starting at a state therein could be controlled to reach a given target set without violating constraints under the worst-case disturbance. We address this problem by designing a new value function with a contracting Bellman backup, where the super-zero level set, i.e., the set of states where the value function is evaluated to be non-negative, recovers the reach-avoid set. Building upon this, we prove th"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2203.10142","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.SY","submitted_at":"2022-03-18T19:48:19Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SY","math.OC"],"title_canon_sha256":"2483c0121034b02c2116e5e69ac8654ad376f7f0a668991f4674012445ca89d0","abstract_canon_sha256":"a48513b506f30b7ec2648d324478cd0a81d9f971c69c3a80981756eba937ff39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:18.271234Z","signature_b64":"3hgi/LnkH0JRgT9gy2eW3uOClaspksQmAdy7+NAFv3vk/zEP4UyN9Jw7zAr4WxSpMGUIQFGWccub1cYV5tbACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b8481fc0b68620560e58b659812d9fdbbabd933d5e7309f787caad4efa1212a","last_reissued_at":"2026-07-05T09:08:18.270723Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:18.270723Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Infinite-Horizon Reach-Avoid Zero-Sum Games via Deep Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SY","math.OC"],"primary_cat":"eess.SY","authors_text":"Claire J. Tomlin, Donggun Lee, Jingqi Li, Somayeh Sojoudi","submitted_at":"2022-03-18T19:48:19Z","abstract_excerpt":"In this paper, we consider the infinite-horizon reach-avoid zero-sum game problem, where the goal is to find a set in the state space, referred to as the reach-avoid set, such that the system starting at a state therein could be controlled to reach a given target set without violating constraints under the worst-case disturbance. We address this problem by designing a new value function with a contracting Bellman backup, where the super-zero level set, i.e., the set of states where the value function is evaluated to be non-negative, recovers the reach-avoid set. Building upon this, we prove th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10142","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.10142/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2203.10142","created_at":"2026-07-05T09:08:18.270791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10142v3","created_at":"2026-07-05T09:08:18.270791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10142","created_at":"2026-07-05T09:08:18.270791+00:00"},{"alias_kind":"pith_short_12","alias_value":"LOCID7ALNBRA","created_at":"2026-07-05T09:08:18.270791+00:00"},{"alias_kind":"pith_short_16","alias_value":"LOCID7ALNBRAKYHF","created_at":"2026-07-05T09:08:18.270791+00:00"},{"alias_kind":"pith_short_8","alias_value":"LOCID7AL","created_at":"2026-07-05T09:08:18.270791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.04276","citing_title":"Bridging Adaptivity and Safety: Learning Agile Collision-Free Locomotion Across Varied Physics","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LOCID7ALNBRAKYHFRNSZQEWZ7W","json":"https://pith.science/pith/LOCID7ALNBRAKYHFRNSZQEWZ7W.json","graph_json":"https://pith.science/api/pith-number/LOCID7ALNBRAKYHFRNSZQEWZ7W/graph.json","events_json":"https://pith.science/api/pith-number/LOCID7ALNBRAKYHFRNSZQEWZ7W/events.json","paper":"https://pith.science/paper/LOCID7AL"},"agent_actions":{"view_html":"https://pith.science/pith/LOCID7ALNBRAKYHFRNSZQEWZ7W","download_json":"https://pith.science/pith/LOCID7ALNBRAKYHFRNSZQEWZ7W.json","view_paper":"https://pith.science/paper/LOCID7AL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10142&json=true","fetch_graph":"https://pith.science/api/pith-number/LOCID7ALNBRAKYHFRNSZQEWZ7W/graph.json","fetch_events":"https://pith.science/api/pith-number/LOCID7ALNBRAKYHFRNSZQEWZ7W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LOCID7ALNBRAKYHFRNSZQEWZ7W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LOCID7ALNBRAKYHFRNSZQEWZ7W/action/storage_attestation","attest_author":"https://pith.science/pith/LOCID7ALNBRAKYHFRNSZQEWZ7W/action/author_attestation","sign_citation":"https://pith.science/pith/LOCID7ALNBRAKYHFRNSZQEWZ7W/action/citation_signature","submit_replication":"https://pith.science/pith/LOCID7ALNBRAKYHFRNSZQEWZ7W/action/replication_record"}},"created_at":"2026-07-05T09:08:18.270791+00:00","updated_at":"2026-07-05T09:08:18.270791+00:00"}