{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:NISC6NXYVNDLKA5YPRTRD2AQ5Z","short_pith_number":"pith:NISC6NXY","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"},"canonical_sha256":"6a242f36f8ab46b503b87c6711e810ee5ab38a63a6e142da497f722b28e4fa08","source":{"kind":"arxiv","id":"2210.12566","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12566","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12566v2","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12566","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"pith_short_12","alias_value":"NISC6NXYVNDL","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"pith_short_16","alias_value":"NISC6NXYVNDLKA5Y","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"pith_short_8","alias_value":"NISC6NXY","created_at":"2026-07-05T06:54:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:NISC6NXYVNDLKA5YPRTRD2AQ5Z","target":"record","payload":{"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"},"canonical_sha256":"6a242f36f8ab46b503b87c6711e810ee5ab38a63a6e142da497f722b28e4fa08","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"},"source_kind":"arxiv","source_id":"2210.12566","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:54:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TCdngvdv9jMBBaL2W2RcfP2V0GrzEE5/7k3deUVhhgxHYod2/MpgsAaxEtVGLeWt+1v3QV7hGyZuZDbdu38pCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T05:14:42.135900Z"},"content_sha256":"4626b94b16aa88ed317f8f7112dc96ddbc1f58117489e0f9d706e431a152d687","schema_version":"1.0","event_id":"sha256:4626b94b16aa88ed317f8f7112dc96ddbc1f58117489e0f9d706e431a152d687"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:NISC6NXYVNDLKA5YPRTRD2AQ5Z","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:54:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RTBY3xh87KHBjUvhjNRBAFkuRsHoqZGQLX5PCrKxHmDeJvos2MEeqM0TM6jnjsxpTSjfwMWDwvs1zco5ZvhyAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T05:14:42.136272Z"},"content_sha256":"eef40fe81b3921d87800e42aca6f10213e23713e806dd71ff5f550885171864e","schema_version":"1.0","event_id":"sha256:eef40fe81b3921d87800e42aca6f10213e23713e806dd71ff5f550885171864e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/bundle.json","state_url":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-10T05:14:42Z","links":{"resolver":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z","bundle":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/bundle.json","state":"https://pith.science/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NISC6NXYVNDLKA5YPRTRD2AQ5Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:NISC6NXYVNDLKA5YPRTRD2AQ5Z","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7b41453fc22699072ac4cf8d4de4a31a6f278f911de3aee6785e0695a01e3894","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T22:55:50Z","title_canon_sha256":"380ccb08b80eb31536ede747f55bcf4c5d97c690a813031bf235a6446f68a9bc"},"schema_version":"1.0","source":{"id":"2210.12566","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.12566","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"arxiv_version","alias_value":"2210.12566v2","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.12566","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"pith_short_12","alias_value":"NISC6NXYVNDL","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"pith_short_16","alias_value":"NISC6NXYVNDLKA5Y","created_at":"2026-07-05T06:54:13Z"},{"alias_kind":"pith_short_8","alias_value":"NISC6NXY","created_at":"2026-07-05T06:54:13Z"}],"graph_snapshots":[{"event_id":"sha256:eef40fe81b3921d87800e42aca6f10213e23713e806dd71ff5f550885171864e","target":"graph","created_at":"2026-07-05T06:54:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.12566/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Daniela Rus, Igor Gilitschenski, Markus Wulfmeier, Martin Riedmiller, Peter Werner, Tim Seyde, Wilko Schwarting","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T22:55:50Z","title":"Solving Continuous Control via Q-learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.12566","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4626b94b16aa88ed317f8f7112dc96ddbc1f58117489e0f9d706e431a152d687","target":"record","created_at":"2026-07-05T06:54:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7b41453fc22699072ac4cf8d4de4a31a6f278f911de3aee6785e0695a01e3894","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-22T22:55:50Z","title_canon_sha256":"380ccb08b80eb31536ede747f55bcf4c5d97c690a813031bf235a6446f68a9bc"},"schema_version":"1.0","source":{"id":"2210.12566","kind":"arxiv","version":2}},"canonical_sha256":"6a242f36f8ab46b503b87c6711e810ee5ab38a63a6e142da497f722b28e4fa08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a242f36f8ab46b503b87c6711e810ee5ab38a63a6e142da497f722b28e4fa08","first_computed_at":"2026-07-05T06:54:13.528863Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:54:13.528863Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WMIitDasErRioOJLezdL41dR1l2hep7Ev5cO/yc9TJ5i9E9Cc4G5WLvKbow0sIIJk0iNIJ+zejAXadhBtHROBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:54:13.529263Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.12566","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4626b94b16aa88ed317f8f7112dc96ddbc1f58117489e0f9d706e431a152d687","sha256:eef40fe81b3921d87800e42aca6f10213e23713e806dd71ff5f550885171864e"],"state_sha256":"84ebc991ffa325a6a734e59d399385e7fa234378f54b60067fd4b4a667a51b7b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cXBsk/voSNK4n44us+Ujpzpop4I7cbASrnJtY6a/9VhMOdN5g1cUnyiQweK0Q73tn7re/cARzaJGI6VyMvDGAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T05:14:42.138471Z","bundle_sha256":"f4a52c41ef35b812acdc1ad510c5801d2a6ec01de9923995c4d8d8ae7ded9426"}}