{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7ZBDG7GV4RFFMZFX5QRVUK24PG","short_pith_number":"pith:7ZBDG7GV","schema_version":"1.0","canonical_sha256":"fe42337cd5e44a5664b7ec235a2b5c79a2d1ce4c14f516396928c67adc86eb51","source":{"kind":"arxiv","id":"2304.02370","version":2},"attestation_state":"computed","paper":{"title":"Effective control of two-dimensional Rayleigh--B\\'enard convection: invariant multi-agent reinforcement learning is all you need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.flu-dyn","authors_text":"Colin Vignon, Francisco Alc\\'antara-\\'Avila, Jean Rabault, Joel Vasanth, Mikael Mortensen, Ricardo Vinuesa","submitted_at":"2023-04-05T11:21:21Z","abstract_excerpt":"Rayleigh-B\\'enard convection (RBC) is a recurrent phenomenon in several industrial and geoscience flows and a well-studied system from a fundamental fluid-mechanics viewpoint. However, controlling RBC, for example by modulating the spatial distribution of the bottom-plate heating in the canonical RBC configuration, remains a challenging topic for classical control-theory methods. In the present work, we apply deep reinforcement learning (DRL) for controlling RBC. We show that effective RBC control can be obtained by leveraging invariant multi-agent reinforcement learning (MARL), which takes ad"},"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":"2304.02370","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.flu-dyn","submitted_at":"2023-04-05T11:21:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b7509240f539252598adfcc2c1d7399dfa0d2618cbfe07953ca514844ab4a9d8","abstract_canon_sha256":"1d56d3f4009111ce315b4e3ab5e305a504475f845a7130ce7a58983512c19de3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:45.652261Z","signature_b64":"Khn6cGrcy8gPdgt7XLkXrf1CCVB0pjMK+87qT8MkFBI2U2XMKiY3BsED/erhcGBe0Feb237iRnFBm22H4C+nAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe42337cd5e44a5664b7ec235a2b5c79a2d1ce4c14f516396928c67adc86eb51","last_reissued_at":"2026-07-05T06:29:45.651603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:45.651603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Effective control of two-dimensional Rayleigh--B\\'enard convection: invariant multi-agent reinforcement learning is all you need","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.flu-dyn","authors_text":"Colin Vignon, Francisco Alc\\'antara-\\'Avila, Jean Rabault, Joel Vasanth, Mikael Mortensen, Ricardo Vinuesa","submitted_at":"2023-04-05T11:21:21Z","abstract_excerpt":"Rayleigh-B\\'enard convection (RBC) is a recurrent phenomenon in several industrial and geoscience flows and a well-studied system from a fundamental fluid-mechanics viewpoint. However, controlling RBC, for example by modulating the spatial distribution of the bottom-plate heating in the canonical RBC configuration, remains a challenging topic for classical control-theory methods. In the present work, we apply deep reinforcement learning (DRL) for controlling RBC. We show that effective RBC control can be obtained by leveraging invariant multi-agent reinforcement learning (MARL), which takes ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.02370","kind":"arxiv","version":2},"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/2304.02370/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":"2304.02370","created_at":"2026-07-05T06:29:45.651685+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.02370v2","created_at":"2026-07-05T06:29:45.651685+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.02370","created_at":"2026-07-05T06:29:45.651685+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZBDG7GV4RFF","created_at":"2026-07-05T06:29:45.651685+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZBDG7GV4RFFMZFX","created_at":"2026-07-05T06:29:45.651685+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZBDG7GV","created_at":"2026-07-05T06:29:45.651685+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06497","citing_title":"Hyperfastrl: Hypernetwork-based reinforcement learning for unified control of parametric chaotic PDEs","ref_index":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ZBDG7GV4RFFMZFX5QRVUK24PG","json":"https://pith.science/pith/7ZBDG7GV4RFFMZFX5QRVUK24PG.json","graph_json":"https://pith.science/api/pith-number/7ZBDG7GV4RFFMZFX5QRVUK24PG/graph.json","events_json":"https://pith.science/api/pith-number/7ZBDG7GV4RFFMZFX5QRVUK24PG/events.json","paper":"https://pith.science/paper/7ZBDG7GV"},"agent_actions":{"view_html":"https://pith.science/pith/7ZBDG7GV4RFFMZFX5QRVUK24PG","download_json":"https://pith.science/pith/7ZBDG7GV4RFFMZFX5QRVUK24PG.json","view_paper":"https://pith.science/paper/7ZBDG7GV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.02370&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZBDG7GV4RFFMZFX5QRVUK24PG/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZBDG7GV4RFFMZFX5QRVUK24PG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZBDG7GV4RFFMZFX5QRVUK24PG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZBDG7GV4RFFMZFX5QRVUK24PG/action/storage_attestation","attest_author":"https://pith.science/pith/7ZBDG7GV4RFFMZFX5QRVUK24PG/action/author_attestation","sign_citation":"https://pith.science/pith/7ZBDG7GV4RFFMZFX5QRVUK24PG/action/citation_signature","submit_replication":"https://pith.science/pith/7ZBDG7GV4RFFMZFX5QRVUK24PG/action/replication_record"}},"created_at":"2026-07-05T06:29:45.651685+00:00","updated_at":"2026-07-05T06:29:45.651685+00:00"}