{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:BR2UF3WFZGLAEHO7XJ4UZS7IHF","short_pith_number":"pith:BR2UF3WF","schema_version":"1.0","canonical_sha256":"0c7542eec5c996021ddfba794ccbe839546604e424b3075b9419ecee2eb1aba4","source":{"kind":"arxiv","id":"1907.13196","version":4},"attestation_state":"computed","paper":{"title":"Wasserstein Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haitham Bou Ammar, Hang Ren, Jun Wang, Mingtian Zhang, Mohammed Amin Abdullah, Rui Luo, Vladimir Milenkovic","submitted_at":"2019-07-30T19:42:52Z","abstract_excerpt":"Reinforcement learning algorithms, though successful, tend to over-fit to training environments hampering their application to the real-world. This paper proposes $\\text{W}\\text{R}^{2}\\text{L}$ -- a robust reinforcement learning algorithm with significant robust performance on low and high-dimensional control tasks. Our method formalises robust reinforcement learning as a novel min-max game with a Wasserstein constraint for a correct and convergent solver. Apart from the formulation, we also propose an efficient and scalable solver following a novel zero-order optimisation method that we belie"},"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":"1907.13196","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-30T19:42:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"202dd118c05a43ef82a074f4153da1b4587bfce8da000f96f4adfe27deefd3da","abstract_canon_sha256":"064136f7ef4c09e9ed8c63b86c17ed27518dd216e0e1d8b93894cb9ac99fa01d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:56.741348Z","signature_b64":"OjSaP58BpIT91sxboTGIdJiaclAoBej7XaRAEvEsRl03ons8wd4er0IfUB4PGKQU09bNCzS2SAiqDuNE+dXCBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c7542eec5c996021ddfba794ccbe839546604e424b3075b9419ecee2eb1aba4","last_reissued_at":"2026-07-05T00:04:56.740916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:56.740916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wasserstein Robust Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Haitham Bou Ammar, Hang Ren, Jun Wang, Mingtian Zhang, Mohammed Amin Abdullah, Rui Luo, Vladimir Milenkovic","submitted_at":"2019-07-30T19:42:52Z","abstract_excerpt":"Reinforcement learning algorithms, though successful, tend to over-fit to training environments hampering their application to the real-world. This paper proposes $\\text{W}\\text{R}^{2}\\text{L}$ -- a robust reinforcement learning algorithm with significant robust performance on low and high-dimensional control tasks. Our method formalises robust reinforcement learning as a novel min-max game with a Wasserstein constraint for a correct and convergent solver. Apart from the formulation, we also propose an efficient and scalable solver following a novel zero-order optimisation method that we belie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.13196","kind":"arxiv","version":4},"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/1907.13196/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":"1907.13196","created_at":"2026-07-05T00:04:56.740974+00:00"},{"alias_kind":"arxiv_version","alias_value":"1907.13196v4","created_at":"2026-07-05T00:04:56.740974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.13196","created_at":"2026-07-05T00:04:56.740974+00:00"},{"alias_kind":"pith_short_12","alias_value":"BR2UF3WFZGLA","created_at":"2026-07-05T00:04:56.740974+00:00"},{"alias_kind":"pith_short_16","alias_value":"BR2UF3WFZGLAEHO7","created_at":"2026-07-05T00:04:56.740974+00:00"},{"alias_kind":"pith_short_8","alias_value":"BR2UF3WF","created_at":"2026-07-05T00:04:56.740974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18143","citing_title":"Distributional Off-Policy Evaluation with Deep Quantile Process Regression","ref_index":162,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10974","citing_title":"Robust Adversarial Policy Optimization Under Dynamics Uncertainty","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF","json":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF.json","graph_json":"https://pith.science/api/pith-number/BR2UF3WFZGLAEHO7XJ4UZS7IHF/graph.json","events_json":"https://pith.science/api/pith-number/BR2UF3WFZGLAEHO7XJ4UZS7IHF/events.json","paper":"https://pith.science/paper/BR2UF3WF"},"agent_actions":{"view_html":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF","download_json":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF.json","view_paper":"https://pith.science/paper/BR2UF3WF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1907.13196&json=true","fetch_graph":"https://pith.science/api/pith-number/BR2UF3WFZGLAEHO7XJ4UZS7IHF/graph.json","fetch_events":"https://pith.science/api/pith-number/BR2UF3WFZGLAEHO7XJ4UZS7IHF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/action/storage_attestation","attest_author":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/action/author_attestation","sign_citation":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/action/citation_signature","submit_replication":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/action/replication_record"}},"created_at":"2026-07-05T00:04:56.740974+00:00","updated_at":"2026-07-05T00:04:56.740974+00:00"}