{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:N7DGQ7DZXBLSG5DYTTY2OBZHLN","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":"66f4b502e53daa7ab0f614c321255d08a1367b1f645b52ee5c3de9fd4e55e762","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2021-09-22T17:59:24Z","title_canon_sha256":"850fa97327d58fddd4c946fb6c8292da50e5f04ce7dccfda5601bd417fa159d2"},"schema_version":"1.0","source":{"id":"2109.10900","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.10900","created_at":"2026-07-05T03:33:49Z"},{"alias_kind":"arxiv_version","alias_value":"2109.10900v2","created_at":"2026-07-05T03:33:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10900","created_at":"2026-07-05T03:33:49Z"},{"alias_kind":"pith_short_12","alias_value":"N7DGQ7DZXBLS","created_at":"2026-07-05T03:33:49Z"},{"alias_kind":"pith_short_16","alias_value":"N7DGQ7DZXBLSG5DY","created_at":"2026-07-05T03:33:49Z"},{"alias_kind":"pith_short_8","alias_value":"N7DGQ7DZ","created_at":"2026-07-05T03:33:49Z"}],"graph_snapshots":[{"event_id":"sha256:83c675fbcebfd013502f4d6eca39bb8ed05a7dd89f5f6fbada4ea3ed90020429","target":"graph","created_at":"2026-07-05T03:33:49Z","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/2109.10900/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning has driven impressive advances in machine learning. Simultaneously, quantum-enhanced machine learning algorithms using quantum annealing underlie heavy developments. Recently, a multi-agent reinforcement learning (MARL) architecture combining both paradigms has been proposed. This novel algorithm, which utilizes Quantum Boltzmann Machines (QBMs) for Q-value approximation has outperformed regular deep reinforcement learning in terms of time-steps needed to converge. However, this algorithm was restricted to single-agent and small 2x2 multi-agent grid domains. In this work","authors_text":"Christoph Roch, Kyrill Schmid, Philipp Altmann, Tobias M\\\"uller","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2021-09-22T17:59:24Z","title":"Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10900","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":"sha256:70b430dbfceffb728eee7f913fb906414a5042d35fa439f97e14796f282b998a","target":"record","created_at":"2026-07-05T03:33:49Z","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":"66f4b502e53daa7ab0f614c321255d08a1367b1f645b52ee5c3de9fd4e55e762","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2021-09-22T17:59:24Z","title_canon_sha256":"850fa97327d58fddd4c946fb6c8292da50e5f04ce7dccfda5601bd417fa159d2"},"schema_version":"1.0","source":{"id":"2109.10900","kind":"arxiv","version":2}},"canonical_sha256":"6fc6687c79b8572374789cf1a707275b4f4517f78754f44ace85e071128bc2f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6fc6687c79b8572374789cf1a707275b4f4517f78754f44ace85e071128bc2f1","first_computed_at":"2026-07-05T03:33:49.940904Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:49.940904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fwBQAyq9ssh+jLaSWg2W7cAbOaHQ/MHkCBGegaz8JTsaKf5nvuYcvdBUmhZaG8lhL+F7ceqdsDQ+zrFW01nxBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:49.941398Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.10900","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:70b430dbfceffb728eee7f913fb906414a5042d35fa439f97e14796f282b998a","sha256:83c675fbcebfd013502f4d6eca39bb8ed05a7dd89f5f6fbada4ea3ed90020429"],"state_sha256":"90e4001eaf5b53091710344764e3e79b987efe012e9b2920fa1e7f038af723cb"}