{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:XLTD2EFNCXAMDAEX3AERY7PBOI","short_pith_number":"pith:XLTD2EFN","schema_version":"1.0","canonical_sha256":"bae63d10ad15c0c18097d8091c7de172323e9ced6810f201fceacd9fe87ff144","source":{"kind":"arxiv","id":"1911.00887","version":3},"attestation_state":"computed","paper":{"title":"Online Robustness Training for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marc Fischer, Martin Vechev, Matthew Mirman, Steven Stalder","submitted_at":"2019-11-03T13:44:42Z","abstract_excerpt":"In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks, while preserving competitive performance. We show that RS-DQN can be combined with (i) state-of-the-art adversarial training and (ii) provably robust training to obtain an agent that is resilient to strong attacks during training and evaluation."},"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":"1911.00887","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-03T13:44:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"af42d0e37e0a460bb0c9f520d96b3b6c8badc27c120dc90f1b9736f765cf767f","abstract_canon_sha256":"524da01f9e3c2ebd8ceb483dc3eb0c519e6201c3b15e2e76272f96ab8ecbacc5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:21:15.856439Z","signature_b64":"mppvt1OOGSXo1XE379GS/3tRvjQuZSmPxHUaMxB1HuZSEh2QDzBBsm8XuahYBnVqN8BRC7VauVbqnKhUjje9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bae63d10ad15c0c18097d8091c7de172323e9ced6810f201fceacd9fe87ff144","last_reissued_at":"2026-07-05T00:21:15.855892Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:21:15.855892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Robustness Training for Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Marc Fischer, Martin Vechev, Matthew Mirman, Steven Stalder","submitted_at":"2019-11-03T13:44:42Z","abstract_excerpt":"In deep reinforcement learning (RL), adversarial attacks can trick an agent into unwanted states and disrupt training. We propose a system called Robust Student-DQN (RS-DQN), which permits online robustness training alongside Q networks, while preserving competitive performance. We show that RS-DQN can be combined with (i) state-of-the-art adversarial training and (ii) provably robust training to obtain an agent that is resilient to strong attacks during training and evaluation."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.00887","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/1911.00887/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":"1911.00887","created_at":"2026-07-05T00:21:15.855955+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.00887v3","created_at":"2026-07-05T00:21:15.855955+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.00887","created_at":"2026-07-05T00:21:15.855955+00:00"},{"alias_kind":"pith_short_12","alias_value":"XLTD2EFNCXAM","created_at":"2026-07-05T00:21:15.855955+00:00"},{"alias_kind":"pith_short_16","alias_value":"XLTD2EFNCXAMDAEX","created_at":"2026-07-05T00:21:15.855955+00:00"},{"alias_kind":"pith_short_8","alias_value":"XLTD2EFN","created_at":"2026-07-05T00:21:15.855955+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17070","citing_title":"Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach","ref_index":35,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XLTD2EFNCXAMDAEX3AERY7PBOI","json":"https://pith.science/pith/XLTD2EFNCXAMDAEX3AERY7PBOI.json","graph_json":"https://pith.science/api/pith-number/XLTD2EFNCXAMDAEX3AERY7PBOI/graph.json","events_json":"https://pith.science/api/pith-number/XLTD2EFNCXAMDAEX3AERY7PBOI/events.json","paper":"https://pith.science/paper/XLTD2EFN"},"agent_actions":{"view_html":"https://pith.science/pith/XLTD2EFNCXAMDAEX3AERY7PBOI","download_json":"https://pith.science/pith/XLTD2EFNCXAMDAEX3AERY7PBOI.json","view_paper":"https://pith.science/paper/XLTD2EFN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.00887&json=true","fetch_graph":"https://pith.science/api/pith-number/XLTD2EFNCXAMDAEX3AERY7PBOI/graph.json","fetch_events":"https://pith.science/api/pith-number/XLTD2EFNCXAMDAEX3AERY7PBOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XLTD2EFNCXAMDAEX3AERY7PBOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XLTD2EFNCXAMDAEX3AERY7PBOI/action/storage_attestation","attest_author":"https://pith.science/pith/XLTD2EFNCXAMDAEX3AERY7PBOI/action/author_attestation","sign_citation":"https://pith.science/pith/XLTD2EFNCXAMDAEX3AERY7PBOI/action/citation_signature","submit_replication":"https://pith.science/pith/XLTD2EFNCXAMDAEX3AERY7PBOI/action/replication_record"}},"created_at":"2026-07-05T00:21:15.855955+00:00","updated_at":"2026-07-05T00:21:15.855955+00:00"}