{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:QFKFT5PDLQO7DWHHSIN2HZLRIG","short_pith_number":"pith:QFKFT5PD","schema_version":"1.0","canonical_sha256":"815459f5e35c1df1d8e7921ba3e57141b7f8955ef501cfb18ded9d57e5b446bb","source":{"kind":"arxiv","id":"2007.07176","version":1},"attestation_state":"computed","paper":{"title":"Robustifying Reinforcement Learning Agents via Action Space Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aakanksha, Kai Liang Tan, Soumik Sarkar, Xian Yeow Lee, Yasaman Esfandiari","submitted_at":"2020-07-14T16:50:02Z","abstract_excerpt":"Adoption of machine learning (ML)-enabled cyber-physical systems (CPS) are becoming prevalent in various sectors of modern society such as transportation, industrial, and power grids. Recent studies in deep reinforcement learning (DRL) have demonstrated its benefits in a large variety of data-driven decisions and control applications. As reliance on ML-enabled systems grows, it is imperative to study the performance of these systems under malicious state and actuator attacks. Traditional control systems employ resilient/fault-tolerant controllers that counter these attacks by correcting the sy"},"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":"2007.07176","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-14T16:50:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f6229b6a14b866b9227f14344df0e547818ce19f472fafff62fb43861366a8c3","abstract_canon_sha256":"842bc55e56bd8e59b143293ac9439aef2f761d9218d2ea081531e2d3b7f73035"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:19:12.635482Z","signature_b64":"9Wh+KOiXe3tfD+b6ZVB9XL0McnShBOpNvNYo2ZjPEw8pucOyY7rGh7mhnq2SznGGOpktjE0Nj6zJBg2WUSvKBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"815459f5e35c1df1d8e7921ba3e57141b7f8955ef501cfb18ded9d57e5b446bb","last_reissued_at":"2026-07-05T01:19:12.635084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:19:12.635084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustifying Reinforcement Learning Agents via Action Space Adversarial Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aakanksha, Kai Liang Tan, Soumik Sarkar, Xian Yeow Lee, Yasaman Esfandiari","submitted_at":"2020-07-14T16:50:02Z","abstract_excerpt":"Adoption of machine learning (ML)-enabled cyber-physical systems (CPS) are becoming prevalent in various sectors of modern society such as transportation, industrial, and power grids. Recent studies in deep reinforcement learning (DRL) have demonstrated its benefits in a large variety of data-driven decisions and control applications. As reliance on ML-enabled systems grows, it is imperative to study the performance of these systems under malicious state and actuator attacks. Traditional control systems employ resilient/fault-tolerant controllers that counter these attacks by correcting the sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.07176","kind":"arxiv","version":1},"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/2007.07176/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":"2007.07176","created_at":"2026-07-05T01:19:12.635152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.07176v1","created_at":"2026-07-05T01:19:12.635152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.07176","created_at":"2026-07-05T01:19:12.635152+00:00"},{"alias_kind":"pith_short_12","alias_value":"QFKFT5PDLQO7","created_at":"2026-07-05T01:19:12.635152+00:00"},{"alias_kind":"pith_short_16","alias_value":"QFKFT5PDLQO7DWHH","created_at":"2026-07-05T01:19:12.635152+00:00"},{"alias_kind":"pith_short_8","alias_value":"QFKFT5PD","created_at":"2026-07-05T01:19:12.635152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QFKFT5PDLQO7DWHHSIN2HZLRIG","json":"https://pith.science/pith/QFKFT5PDLQO7DWHHSIN2HZLRIG.json","graph_json":"https://pith.science/api/pith-number/QFKFT5PDLQO7DWHHSIN2HZLRIG/graph.json","events_json":"https://pith.science/api/pith-number/QFKFT5PDLQO7DWHHSIN2HZLRIG/events.json","paper":"https://pith.science/paper/QFKFT5PD"},"agent_actions":{"view_html":"https://pith.science/pith/QFKFT5PDLQO7DWHHSIN2HZLRIG","download_json":"https://pith.science/pith/QFKFT5PDLQO7DWHHSIN2HZLRIG.json","view_paper":"https://pith.science/paper/QFKFT5PD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.07176&json=true","fetch_graph":"https://pith.science/api/pith-number/QFKFT5PDLQO7DWHHSIN2HZLRIG/graph.json","fetch_events":"https://pith.science/api/pith-number/QFKFT5PDLQO7DWHHSIN2HZLRIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QFKFT5PDLQO7DWHHSIN2HZLRIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QFKFT5PDLQO7DWHHSIN2HZLRIG/action/storage_attestation","attest_author":"https://pith.science/pith/QFKFT5PDLQO7DWHHSIN2HZLRIG/action/author_attestation","sign_citation":"https://pith.science/pith/QFKFT5PDLQO7DWHHSIN2HZLRIG/action/citation_signature","submit_replication":"https://pith.science/pith/QFKFT5PDLQO7DWHHSIN2HZLRIG/action/replication_record"}},"created_at":"2026-07-05T01:19:12.635152+00:00","updated_at":"2026-07-05T01:19:12.635152+00:00"}