{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:G4ONBQPXTSZKNJW6WBS6XVB3HR","short_pith_number":"pith:G4ONBQPX","schema_version":"1.0","canonical_sha256":"371cd0c1f79cb2a6a6deb065ebd43b3c7e0a8acca1ed1720301250758d629e63","source":{"kind":"arxiv","id":"2406.08406","version":1},"attestation_state":"computed","paper":{"title":"RRLS : Robust Reinforcement Learning Suite","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adil Zouitine, David Bertoin, Emmanuel Rachelson, Matthieu Geist, Pierre Clavier","submitted_at":"2024-06-12T16:53:51Z","abstract_excerpt":"Robust reinforcement learning is the problem of learning control policies that provide optimal worst-case performance against a span of adversarial environments. It is a crucial ingredient for deploying algorithms in real-world scenarios with prevalent environmental uncertainties and has been a long-standing object of attention in the community, without a standardized set of benchmarks. This contribution endeavors to fill this gap. We introduce the Robust Reinforcement Learning Suite (RRLS), a benchmark suite based on Mujoco environments. RRLS provides six continuous control tasks with two typ"},"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":"2406.08406","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-12T16:53:51Z","cross_cats_sorted":[],"title_canon_sha256":"96c5b7f00bfb798f534ea08f84acdc45234f0ef16696a692919867b7f17d8f9b","abstract_canon_sha256":"6734a838b0a64a0ef19410b9154c16b8f36e58f4ecaee7fb9b668ae73799b8c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:30:59.294507Z","signature_b64":"iO1yLf8MGhazp/uqvQ9wedgqY35rkMubmBjHqyxgV+skaIrD7s02V83xujY7aMxSp/MP8gDAxmw3R1iRzA4SDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"371cd0c1f79cb2a6a6deb065ebd43b3c7e0a8acca1ed1720301250758d629e63","last_reissued_at":"2026-07-05T08:30:59.294023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:30:59.294023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RRLS : Robust Reinforcement Learning Suite","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adil Zouitine, David Bertoin, Emmanuel Rachelson, Matthieu Geist, Pierre Clavier","submitted_at":"2024-06-12T16:53:51Z","abstract_excerpt":"Robust reinforcement learning is the problem of learning control policies that provide optimal worst-case performance against a span of adversarial environments. It is a crucial ingredient for deploying algorithms in real-world scenarios with prevalent environmental uncertainties and has been a long-standing object of attention in the community, without a standardized set of benchmarks. This contribution endeavors to fill this gap. We introduce the Robust Reinforcement Learning Suite (RRLS), a benchmark suite based on Mujoco environments. RRLS provides six continuous control tasks with two typ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08406","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/2406.08406/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":"2406.08406","created_at":"2026-07-05T08:30:59.294083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.08406v1","created_at":"2026-07-05T08:30:59.294083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08406","created_at":"2026-07-05T08:30:59.294083+00:00"},{"alias_kind":"pith_short_12","alias_value":"G4ONBQPXTSZK","created_at":"2026-07-05T08:30:59.294083+00:00"},{"alias_kind":"pith_short_16","alias_value":"G4ONBQPXTSZKNJW6","created_at":"2026-07-05T08:30:59.294083+00:00"},{"alias_kind":"pith_short_8","alias_value":"G4ONBQPX","created_at":"2026-07-05T08:30:59.294083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.00257","citing_title":"Gym4ReaL: A Suite for Benchmarking Real-World Reinforcement Learning","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR","json":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR.json","graph_json":"https://pith.science/api/pith-number/G4ONBQPXTSZKNJW6WBS6XVB3HR/graph.json","events_json":"https://pith.science/api/pith-number/G4ONBQPXTSZKNJW6WBS6XVB3HR/events.json","paper":"https://pith.science/paper/G4ONBQPX"},"agent_actions":{"view_html":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR","download_json":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR.json","view_paper":"https://pith.science/paper/G4ONBQPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.08406&json=true","fetch_graph":"https://pith.science/api/pith-number/G4ONBQPXTSZKNJW6WBS6XVB3HR/graph.json","fetch_events":"https://pith.science/api/pith-number/G4ONBQPXTSZKNJW6WBS6XVB3HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/action/storage_attestation","attest_author":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/action/author_attestation","sign_citation":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/action/citation_signature","submit_replication":"https://pith.science/pith/G4ONBQPXTSZKNJW6WBS6XVB3HR/action/replication_record"}},"created_at":"2026-07-05T08:30:59.294083+00:00","updated_at":"2026-07-05T08:30:59.294083+00:00"}