{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WHLS7OULSTVCMFGZDSKJTUT55A","short_pith_number":"pith:WHLS7OUL","schema_version":"1.0","canonical_sha256":"b1d72fba8b94ea2614d91c9499d27de80df85761a7eb6e4105cfc6ca24812e6b","source":{"kind":"arxiv","id":"2202.06052","version":1},"attestation_state":"computed","paper":{"title":"Learning by Doing: Controlling a Dynamical System using Causality, Control, and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dominik Baumann, Isabelle Guyon, Jonas Peters, Niklas Pfister, Oliver Kroemer, Sebastian Trimpe, Sebastian Weichwald, S{\\o}ren Wengel Mogensen, Tabitha Edith Lee","submitted_at":"2022-02-12T12:37:29Z","abstract_excerpt":"Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i.i.d. observations. Instead, these fields consider the problem of learning how to actively perturb a system to achieve a certain effect on a response variable. Arguably, they have complementary views on the problem: In control, one usually aims to first identify the system by excitation strategies to then apply model-based design techniques to control the system. In (non-model-based) reinforcement learning, one directly optimizes a reward. In causality, one focus is on"},"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":"2202.06052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-02-12T12:37:29Z","cross_cats_sorted":["cs.RO","cs.SY","eess.SY","stat.ME","stat.ML"],"title_canon_sha256":"28f91282a037ff91479a04e3c19772f2fa1264aeed9ff88953346b2de301afa2","abstract_canon_sha256":"6ed4ae8976fefd41d36772335b87742eb9087b14316de961989e4f25757a5f0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:20.289826Z","signature_b64":"x+0eLmUmOV/eJbJKcEi7LB696d2+arU12uSfHDe99VEp4q4eMGYRwvD5CyVgCxDJZPinlKr+TsUca8szGApxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1d72fba8b94ea2614d91c9499d27de80df85761a7eb6e4105cfc6ca24812e6b","last_reissued_at":"2026-07-05T03:56:20.289413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:20.289413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning by Doing: Controlling a Dynamical System using Causality, Control, and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO","cs.SY","eess.SY","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Dominik Baumann, Isabelle Guyon, Jonas Peters, Niklas Pfister, Oliver Kroemer, Sebastian Trimpe, Sebastian Weichwald, S{\\o}ren Wengel Mogensen, Tabitha Edith Lee","submitted_at":"2022-02-12T12:37:29Z","abstract_excerpt":"Questions in causality, control, and reinforcement learning go beyond the classical machine learning task of prediction under i.i.d. observations. Instead, these fields consider the problem of learning how to actively perturb a system to achieve a certain effect on a response variable. Arguably, they have complementary views on the problem: In control, one usually aims to first identify the system by excitation strategies to then apply model-based design techniques to control the system. In (non-model-based) reinforcement learning, one directly optimizes a reward. In causality, one focus is on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06052","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/2202.06052/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":"2202.06052","created_at":"2026-07-05T03:56:20.289471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.06052v1","created_at":"2026-07-05T03:56:20.289471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06052","created_at":"2026-07-05T03:56:20.289471+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHLS7OULSTVC","created_at":"2026-07-05T03:56:20.289471+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHLS7OULSTVCMFGZ","created_at":"2026-07-05T03:56:20.289471+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHLS7OUL","created_at":"2026-07-05T03:56:20.289471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WHLS7OULSTVCMFGZDSKJTUT55A","json":"https://pith.science/pith/WHLS7OULSTVCMFGZDSKJTUT55A.json","graph_json":"https://pith.science/api/pith-number/WHLS7OULSTVCMFGZDSKJTUT55A/graph.json","events_json":"https://pith.science/api/pith-number/WHLS7OULSTVCMFGZDSKJTUT55A/events.json","paper":"https://pith.science/paper/WHLS7OUL"},"agent_actions":{"view_html":"https://pith.science/pith/WHLS7OULSTVCMFGZDSKJTUT55A","download_json":"https://pith.science/pith/WHLS7OULSTVCMFGZDSKJTUT55A.json","view_paper":"https://pith.science/paper/WHLS7OUL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.06052&json=true","fetch_graph":"https://pith.science/api/pith-number/WHLS7OULSTVCMFGZDSKJTUT55A/graph.json","fetch_events":"https://pith.science/api/pith-number/WHLS7OULSTVCMFGZDSKJTUT55A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHLS7OULSTVCMFGZDSKJTUT55A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHLS7OULSTVCMFGZDSKJTUT55A/action/storage_attestation","attest_author":"https://pith.science/pith/WHLS7OULSTVCMFGZDSKJTUT55A/action/author_attestation","sign_citation":"https://pith.science/pith/WHLS7OULSTVCMFGZDSKJTUT55A/action/citation_signature","submit_replication":"https://pith.science/pith/WHLS7OULSTVCMFGZDSKJTUT55A/action/replication_record"}},"created_at":"2026-07-05T03:56:20.289471+00:00","updated_at":"2026-07-05T03:56:20.289471+00:00"}