{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BR2UF3WFZGLAEHO7XJ4UZS7IHF","short_pith_number":"pith:BR2UF3WF","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"},"canonical_sha256":"0c7542eec5c996021ddfba794ccbe839546604e424b3075b9419ecee2eb1aba4","source":{"kind":"arxiv","id":"1907.13196","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.13196","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"1907.13196v4","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.13196","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"BR2UF3WFZGLA","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"BR2UF3WFZGLAEHO7","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"BR2UF3WF","created_at":"2026-07-05T00:04:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BR2UF3WFZGLAEHO7XJ4UZS7IHF","target":"record","payload":{"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"},"canonical_sha256":"0c7542eec5c996021ddfba794ccbe839546604e424b3075b9419ecee2eb1aba4","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"},"source_kind":"arxiv","source_id":"1907.13196","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d5F+Glr+nr7hqieC+pGHI0YxJzhrUHTRJnyL9lUv9wqc9UAP3LqK6Iup1HqtMl7JF5H16DSu8nBHEgWTJLrdAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:45:11.503663Z"},"content_sha256":"fe01c4a72bb888f9988c14cb3d40266cafb05c4d8a9b26c5c83a58fc6fc958f7","schema_version":"1.0","event_id":"sha256:fe01c4a72bb888f9988c14cb3d40266cafb05c4d8a9b26c5c83a58fc6fc958f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BR2UF3WFZGLAEHO7XJ4UZS7IHF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:04:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ty334BQH/RLP+NPwYLNtzsl/ooHPfEP+/8whVMbt1snOzkBpcHgVHk7Rgk5zhfzbgLsunhoiu8hSefReu7g7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:45:11.504139Z"},"content_sha256":"dbb1a73be3dbe4d2115896d04d716107611b2269e9e1ab7205e59898ab6465b3","schema_version":"1.0","event_id":"sha256:dbb1a73be3dbe4d2115896d04d716107611b2269e9e1ab7205e59898ab6465b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/bundle.json","state_url":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T11:45:11Z","links":{"resolver":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF","bundle":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/bundle.json","state":"https://pith.science/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BR2UF3WFZGLAEHO7XJ4UZS7IHF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BR2UF3WFZGLAEHO7XJ4UZS7IHF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"064136f7ef4c09e9ed8c63b86c17ed27518dd216e0e1d8b93894cb9ac99fa01d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-30T19:42:52Z","title_canon_sha256":"202dd118c05a43ef82a074f4153da1b4587bfce8da000f96f4adfe27deefd3da"},"schema_version":"1.0","source":{"id":"1907.13196","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.13196","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"1907.13196v4","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.13196","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"BR2UF3WFZGLA","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"BR2UF3WFZGLAEHO7","created_at":"2026-07-05T00:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"BR2UF3WF","created_at":"2026-07-05T00:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:dbb1a73be3dbe4d2115896d04d716107611b2269e9e1ab7205e59898ab6465b3","target":"graph","created_at":"2026-07-05T00:04:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1907.13196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Haitham Bou Ammar, Hang Ren, Jun Wang, Mingtian Zhang, Mohammed Amin Abdullah, Rui Luo, Vladimir Milenkovic","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-30T19:42:52Z","title":"Wasserstein Robust Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.13196","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:fe01c4a72bb888f9988c14cb3d40266cafb05c4d8a9b26c5c83a58fc6fc958f7","target":"record","created_at":"2026-07-05T00:04:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"064136f7ef4c09e9ed8c63b86c17ed27518dd216e0e1d8b93894cb9ac99fa01d","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-30T19:42:52Z","title_canon_sha256":"202dd118c05a43ef82a074f4153da1b4587bfce8da000f96f4adfe27deefd3da"},"schema_version":"1.0","source":{"id":"1907.13196","kind":"arxiv","version":4}},"canonical_sha256":"0c7542eec5c996021ddfba794ccbe839546604e424b3075b9419ecee2eb1aba4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0c7542eec5c996021ddfba794ccbe839546604e424b3075b9419ecee2eb1aba4","first_computed_at":"2026-07-05T00:04:56.740916Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:04:56.740916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OjSaP58BpIT91sxboTGIdJiaclAoBej7XaRAEvEsRl03ons8wd4er0IfUB4PGKQU09bNCzS2SAiqDuNE+dXCBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:04:56.741348Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.13196","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe01c4a72bb888f9988c14cb3d40266cafb05c4d8a9b26c5c83a58fc6fc958f7","sha256:dbb1a73be3dbe4d2115896d04d716107611b2269e9e1ab7205e59898ab6465b3"],"state_sha256":"59d3fbc9ea003f196f1f26a4170067334e13ce3e5ea8e0f61bcca17ca9687eac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cmBXL+/fBFRfbpntXRx7IwEuufvNw2ZUaPDSOBRK+lju6tiA9GOCpM+/jlrt2nY27cPBLjk+Rb1Z3CDBrSfMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T11:45:11.508772Z","bundle_sha256":"2001acd9c677b4d7d4384843bc15b4cd24a4305ecb380455d93120b42ef8fd6e"}}