{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4SAPXMW7IH7FV3QED263PBNEOF","short_pith_number":"pith:4SAPXMW7","schema_version":"1.0","canonical_sha256":"e480fbb2df41fe5aee041ebdb785a4717028c47db7818936abe1440f99daac19","source":{"kind":"arxiv","id":"2403.00420","version":3},"attestation_state":"computed","paper":{"title":"Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Elies Gherbi, Frederic Cuppens, Hatem Hajri, Josephine Delas, Lucas Schott, Nora Boulahia-Cuppens, Reda Yaich, Sylvain Lamprier","submitted_at":"2024-03-01T10:16:46Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains susceptible to minor condition variations, raising concerns about its reliability in real-world applications. To improve usability, DRL must demonstrate trustworthiness and robustness. A way to improve the robustness of DRL to unknown changes in the environmental conditions and possible perturbations is through Adversarial Training, by training the agent against wel"},"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":"2403.00420","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-01T10:16:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"235ec41776c9f047e8a18f636aa0d96bb3606412ce8f873e3fccfaeb4b5efcad","abstract_canon_sha256":"474df8e672f129781015738f3e45f565b066b1653a339d7d3191bb6903547bf3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:11.258968Z","signature_b64":"hIcpMKbhqNgGGwKVfFamVFSWucIGaM9vO+2QFguYSPT/0aC7kdU6z44UxXb8TXAKiebRbTvEF6A0iObL+vg8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e480fbb2df41fe5aee041ebdb785a4717028c47db7818936abe1440f99daac19","last_reissued_at":"2026-06-10T01:09:11.257697Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:11.257697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Elies Gherbi, Frederic Cuppens, Hatem Hajri, Josephine Delas, Lucas Schott, Nora Boulahia-Cuppens, Reda Yaich, Sylvain Lamprier","submitted_at":"2024-03-01T10:16:46Z","abstract_excerpt":"Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains susceptible to minor condition variations, raising concerns about its reliability in real-world applications. To improve usability, DRL must demonstrate trustworthiness and robustness. A way to improve the robustness of DRL to unknown changes in the environmental conditions and possible perturbations is through Adversarial Training, by training the agent against wel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00420","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/2403.00420/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":"2403.00420","created_at":"2026-06-10T01:09:11.257872+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00420v3","created_at":"2026-06-10T01:09:11.257872+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00420","created_at":"2026-06-10T01:09:11.257872+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SAPXMW7IH7F","created_at":"2026-06-10T01:09:11.257872+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SAPXMW7IH7FV3QE","created_at":"2026-06-10T01:09:11.257872+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SAPXMW7","created_at":"2026-06-10T01:09:11.257872+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/4SAPXMW7IH7FV3QED263PBNEOF","json":"https://pith.science/pith/4SAPXMW7IH7FV3QED263PBNEOF.json","graph_json":"https://pith.science/api/pith-number/4SAPXMW7IH7FV3QED263PBNEOF/graph.json","events_json":"https://pith.science/api/pith-number/4SAPXMW7IH7FV3QED263PBNEOF/events.json","paper":"https://pith.science/paper/4SAPXMW7"},"agent_actions":{"view_html":"https://pith.science/pith/4SAPXMW7IH7FV3QED263PBNEOF","download_json":"https://pith.science/pith/4SAPXMW7IH7FV3QED263PBNEOF.json","view_paper":"https://pith.science/paper/4SAPXMW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00420&json=true","fetch_graph":"https://pith.science/api/pith-number/4SAPXMW7IH7FV3QED263PBNEOF/graph.json","fetch_events":"https://pith.science/api/pith-number/4SAPXMW7IH7FV3QED263PBNEOF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SAPXMW7IH7FV3QED263PBNEOF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SAPXMW7IH7FV3QED263PBNEOF/action/storage_attestation","attest_author":"https://pith.science/pith/4SAPXMW7IH7FV3QED263PBNEOF/action/author_attestation","sign_citation":"https://pith.science/pith/4SAPXMW7IH7FV3QED263PBNEOF/action/citation_signature","submit_replication":"https://pith.science/pith/4SAPXMW7IH7FV3QED263PBNEOF/action/replication_record"}},"created_at":"2026-06-10T01:09:11.257872+00:00","updated_at":"2026-06-10T01:09:11.257872+00:00"}