{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NISC6NXYVNDLKA5YPRTRD2AQ5Z","short_pith_number":"pith:NISC6NXY","schema_version":"1.0","canonical_sha256":"6a242f36f8ab46b503b87c6711e810ee5ab38a63a6e142da497f722b28e4fa08","source":{"kind":"arxiv","id":"2210.12566","version":2},"attestation_state":"computed","paper":{"title":"Solving Continuous Control via Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Daniela Rus, Igor Gilitschenski, Markus Wulfmeier, Martin Riedmiller, Peter Werner, Tim Seyde, Wilko Schwarting","submitted_at":"2022-10-22T22:55:50Z","abstract_excerpt":"While there has been substantial success for solving continuous control with actor-critic methods, simpler critic-only methods such as Q-learning find limited application in the associated high-dimensional action spaces. However, most actor-critic methods come at the cost of added complexity: heuristics for stabilisation, compute requirements and wider hyperparameter search spaces. We show that a simple modification of deep Q-learning largely alleviates these issues. By combining bang-bang action discretization with value decomposition, framing single-agent control as cooperative multi-agent r"},"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":"2210.12566","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T22:55:50Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"380ccb08b80eb31536ede747f55bcf4c5d97c690a813031bf235a6446f68a9bc","abstract_canon_sha256":"7b41453fc22699072ac4cf8d4de4a31a6f278f911de3aee6785e0695a01e3894"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:54:13.529263Z","signature_b64":"WMIitDasErRioOJLezdL41dR1l2hep7Ev5cO/yc9TJ5i9E9Cc4G5WLvKbow0sIIJk0iNIJ+zejAXadhBtHROBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a242f36f8ab46b503b87c6711e810ee5ab38a63a6e142da497f722b28e4fa08","last_reissued_at":"2026-07-05T06:54:13.528863Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:54:13.528863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Solving Continuous Control via Q-learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.LG","authors_text":"Daniela Rus, Igor Gilitschenski, Markus Wulfmeier, Martin Riedmiller, Peter Werner, Tim Seyde, Wilko Schwarting","submitted_at":"2022-10-22T22:55:50Z","abstract_excerpt":"While there has been substantial success for solving continuous control with actor-critic methods, simpler critic-only methods such as Q-learning find limited application in the associated high-dimensional action spaces. However, most actor-critic methods come at the cost of added complexity: heuristics for stabilisation, compute requirements and wider hyperparameter search spaces. We show that a simple modification of deep Q-learning largely alleviates these issues. By combining bang-bang action discretization with value decomposition, framing single-agent control as cooperative multi-agent r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12566","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/2210.12566/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":"2210.12566","created_at":"2026-07-05T06:54:13.528914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.12566v2","created_at":"2026-07-05T06:54:13.528914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12566","created_at":"2026-07-05T06:54:13.528914+00:00"},{"alias_kind":"pith_short_12","alias_value":"NISC6NXYVNDL","created_at":"2026-07-05T06:54:13.528914+00:00"},{"alias_kind":"pith_short_16","alias_value":"NISC6NXYVNDLKA5Y","created_at":"2026-07-05T06:54:13.528914+00:00"},{"alias_kind":"pith_short_8","alias_value":"NISC6NXY","created_at":"2026-07-05T06:54:13.528914+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/NISC6NXYVNDLKA5YPRTRD2AQ5Z","json":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z.json","graph_json":"https://pith.science/api/pith-number/NISC6NXYVNDLKA5YPRTRD2AQ5Z/graph.json","events_json":"https://pith.science/api/pith-number/NISC6NXYVNDLKA5YPRTRD2AQ5Z/events.json","paper":"https://pith.science/paper/NISC6NXY"},"agent_actions":{"view_html":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z","download_json":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z.json","view_paper":"https://pith.science/paper/NISC6NXY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.12566&json=true","fetch_graph":"https://pith.science/api/pith-number/NISC6NXYVNDLKA5YPRTRD2AQ5Z/graph.json","fetch_events":"https://pith.science/api/pith-number/NISC6NXYVNDLKA5YPRTRD2AQ5Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/action/storage_attestation","attest_author":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/action/author_attestation","sign_citation":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/action/citation_signature","submit_replication":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/action/replication_record"}},"created_at":"2026-07-05T06:54:13.528914+00:00","updated_at":"2026-07-05T06:54:13.528914+00:00"}