{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:N7DGQ7DZXBLSG5DYTTY2OBZHLN","short_pith_number":"pith:N7DGQ7DZ","schema_version":"1.0","canonical_sha256":"6fc6687c79b8572374789cf1a707275b4f4517f78754f44ace85e071128bc2f1","source":{"kind":"arxiv","id":"2109.10900","version":2},"attestation_state":"computed","paper":{"title":"Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Christoph Roch, Kyrill Schmid, Philipp Altmann, Tobias M\\\"uller","submitted_at":"2021-09-22T17:59:24Z","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"},"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":"2109.10900","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2021-09-22T17:59:24Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"850fa97327d58fddd4c946fb6c8292da50e5f04ce7dccfda5601bd417fa159d2","abstract_canon_sha256":"66f4b502e53daa7ab0f614c321255d08a1367b1f645b52ee5c3de9fd4e55e762"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:49.941398Z","signature_b64":"fwBQAyq9ssh+jLaSWg2W7cAbOaHQ/MHkCBGegaz8JTsaKf5nvuYcvdBUmhZaG8lhL+F7ceqdsDQ+zrFW01nxBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6fc6687c79b8572374789cf1a707275b4f4517f78754f44ace85e071128bc2f1","last_reissued_at":"2026-07-05T03:33:49.940904Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:49.940904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Multi-Agent Reinforcement Learning using Quantum Boltzmann Machines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Christoph Roch, Kyrill Schmid, Philipp Altmann, Tobias M\\\"uller","submitted_at":"2021-09-22T17:59:24Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.10900","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/2109.10900/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":"2109.10900","created_at":"2026-07-05T03:33:49.940959+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.10900v2","created_at":"2026-07-05T03:33:49.940959+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.10900","created_at":"2026-07-05T03:33:49.940959+00:00"},{"alias_kind":"pith_short_12","alias_value":"N7DGQ7DZXBLS","created_at":"2026-07-05T03:33:49.940959+00:00"},{"alias_kind":"pith_short_16","alias_value":"N7DGQ7DZXBLSG5DY","created_at":"2026-07-05T03:33:49.940959+00:00"},{"alias_kind":"pith_short_8","alias_value":"N7DGQ7DZ","created_at":"2026-07-05T03:33:49.940959+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04909","citing_title":"Benchmarking Quantum Reinforcement Learning","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N7DGQ7DZXBLSG5DYTTY2OBZHLN","json":"https://pith.science/pith/N7DGQ7DZXBLSG5DYTTY2OBZHLN.json","graph_json":"https://pith.science/api/pith-number/N7DGQ7DZXBLSG5DYTTY2OBZHLN/graph.json","events_json":"https://pith.science/api/pith-number/N7DGQ7DZXBLSG5DYTTY2OBZHLN/events.json","paper":"https://pith.science/paper/N7DGQ7DZ"},"agent_actions":{"view_html":"https://pith.science/pith/N7DGQ7DZXBLSG5DYTTY2OBZHLN","download_json":"https://pith.science/pith/N7DGQ7DZXBLSG5DYTTY2OBZHLN.json","view_paper":"https://pith.science/paper/N7DGQ7DZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.10900&json=true","fetch_graph":"https://pith.science/api/pith-number/N7DGQ7DZXBLSG5DYTTY2OBZHLN/graph.json","fetch_events":"https://pith.science/api/pith-number/N7DGQ7DZXBLSG5DYTTY2OBZHLN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N7DGQ7DZXBLSG5DYTTY2OBZHLN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N7DGQ7DZXBLSG5DYTTY2OBZHLN/action/storage_attestation","attest_author":"https://pith.science/pith/N7DGQ7DZXBLSG5DYTTY2OBZHLN/action/author_attestation","sign_citation":"https://pith.science/pith/N7DGQ7DZXBLSG5DYTTY2OBZHLN/action/citation_signature","submit_replication":"https://pith.science/pith/N7DGQ7DZXBLSG5DYTTY2OBZHLN/action/replication_record"}},"created_at":"2026-07-05T03:33:49.940959+00:00","updated_at":"2026-07-05T03:33:49.940959+00:00"}