{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YS7HGOW222L6UJYIPOJZEVGWA2","short_pith_number":"pith:YS7HGOW2","schema_version":"1.0","canonical_sha256":"c4be733adad697ea27087b939254d606b5ce083816d08d2561fb166a23f91a72","source":{"kind":"arxiv","id":"2407.17822","version":2},"attestation_state":"computed","paper":{"title":"Advanced deep-reinforcement-learning methods for flow control: group-invariant and positional-encoding networks improve learning speed and quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Francisco Alc\\'antara-\\'Avila, Jean Rabault, Joel Vasanth, Joongoo Jeon, Ricardo Vinuesa, Shilaj Baral","submitted_at":"2024-07-25T07:24:41Z","abstract_excerpt":"Flow control is key to maximize energy efficiency in a wide range of applications. However, traditional flow-control methods face significant challenges in addressing non-linear systems and high-dimensional data, limiting their application in realistic energy systems. This study advances deep-reinforcement-learning (DRL) methods for flow control, particularly focusing on integrating group-invariant networks and positional encoding into DRL architectures. Our methods leverage multi-agent reinforcement learning (MARL) to exploit policy invariance in space, in combination with group-invariant net"},"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":"2407.17822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-25T07:24:41Z","cross_cats_sorted":["physics.flu-dyn"],"title_canon_sha256":"64ad4095b79a616f0f5be5df1a87cda9bea679de1e75140dc7cea41efde4bf21","abstract_canon_sha256":"9891ec44e331868ccf00507bd593fc0bdac577e3a0a896009b728b0302c68c82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:45.722164Z","signature_b64":"UzQl1mOX0X7iVodkt04Qr2qiAxMOrexfMtqAhTjZSm2csFlDWFBFcGz3Z8Bt1ZDrljkcb54tSlEsCVMokLCCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4be733adad697ea27087b939254d606b5ce083816d08d2561fb166a23f91a72","last_reissued_at":"2026-07-05T09:25:45.721644Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:45.721644Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Advanced deep-reinforcement-learning methods for flow control: group-invariant and positional-encoding networks improve learning speed and quality","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.flu-dyn"],"primary_cat":"cs.LG","authors_text":"Francisco Alc\\'antara-\\'Avila, Jean Rabault, Joel Vasanth, Joongoo Jeon, Ricardo Vinuesa, Shilaj Baral","submitted_at":"2024-07-25T07:24:41Z","abstract_excerpt":"Flow control is key to maximize energy efficiency in a wide range of applications. However, traditional flow-control methods face significant challenges in addressing non-linear systems and high-dimensional data, limiting their application in realistic energy systems. This study advances deep-reinforcement-learning (DRL) methods for flow control, particularly focusing on integrating group-invariant networks and positional encoding into DRL architectures. Our methods leverage multi-agent reinforcement learning (MARL) to exploit policy invariance in space, in combination with group-invariant net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17822","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/2407.17822/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":"2407.17822","created_at":"2026-07-05T09:25:45.721707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.17822v2","created_at":"2026-07-05T09:25:45.721707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17822","created_at":"2026-07-05T09:25:45.721707+00:00"},{"alias_kind":"pith_short_12","alias_value":"YS7HGOW222L6","created_at":"2026-07-05T09:25:45.721707+00:00"},{"alias_kind":"pith_short_16","alias_value":"YS7HGOW222L6UJYI","created_at":"2026-07-05T09:25:45.721707+00:00"},{"alias_kind":"pith_short_8","alias_value":"YS7HGOW2","created_at":"2026-07-05T09:25:45.721707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30238","citing_title":"Sparse Sensor Placement in Multi-Agent Reinforcement Learning Control of Rayleigh-B\\'enard Convection","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21804","citing_title":"XRePIT: A deep learning-computational fluid dynamics hybrid framework implemented in OpenFOAM for fast, robust, and scalable unsteady simulations","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YS7HGOW222L6UJYIPOJZEVGWA2","json":"https://pith.science/pith/YS7HGOW222L6UJYIPOJZEVGWA2.json","graph_json":"https://pith.science/api/pith-number/YS7HGOW222L6UJYIPOJZEVGWA2/graph.json","events_json":"https://pith.science/api/pith-number/YS7HGOW222L6UJYIPOJZEVGWA2/events.json","paper":"https://pith.science/paper/YS7HGOW2"},"agent_actions":{"view_html":"https://pith.science/pith/YS7HGOW222L6UJYIPOJZEVGWA2","download_json":"https://pith.science/pith/YS7HGOW222L6UJYIPOJZEVGWA2.json","view_paper":"https://pith.science/paper/YS7HGOW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.17822&json=true","fetch_graph":"https://pith.science/api/pith-number/YS7HGOW222L6UJYIPOJZEVGWA2/graph.json","fetch_events":"https://pith.science/api/pith-number/YS7HGOW222L6UJYIPOJZEVGWA2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YS7HGOW222L6UJYIPOJZEVGWA2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YS7HGOW222L6UJYIPOJZEVGWA2/action/storage_attestation","attest_author":"https://pith.science/pith/YS7HGOW222L6UJYIPOJZEVGWA2/action/author_attestation","sign_citation":"https://pith.science/pith/YS7HGOW222L6UJYIPOJZEVGWA2/action/citation_signature","submit_replication":"https://pith.science/pith/YS7HGOW222L6UJYIPOJZEVGWA2/action/replication_record"}},"created_at":"2026-07-05T09:25:45.721707+00:00","updated_at":"2026-07-05T09:25:45.721707+00:00"}