{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GRCFLRHCC62RYYAXYCBURUBYZ7","short_pith_number":"pith:GRCFLRHC","schema_version":"1.0","canonical_sha256":"344455c4e217b51c6017c08348d038cff4c8f16b872337dfa49a9c61bd906860","source":{"kind":"arxiv","id":"2412.14218","version":2},"attestation_state":"computed","paper":{"title":"Heterogeneous Multi-Agent Reinforcement Learning for Distributed Channel Access in WLANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.LG","authors_text":"Chongtao Guo, Geoffrey Ye Li, Jiaming Yu, Le Liang, Shi Jin, Ziyang Guo","submitted_at":"2024-12-18T13:50:31Z","abstract_excerpt":"This paper investigates the use of multi-agent reinforcement learning (MARL) to address distributed channel access in wireless local area networks. In particular, we consider the challenging yet more practical case where the agents heterogeneously adopt value-based or policy-based reinforcement learning algorithms to train the model. We propose a heterogeneous MARL training framework, named QPMIX, which adopts a centralized training with distributed execution paradigm to enable heterogeneous agents to collaborate. Moreover, we theoretically prove the convergence of the proposed heterogeneous M"},"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":"2412.14218","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-18T13:50:31Z","cross_cats_sorted":["cs.AI","cs.NI"],"title_canon_sha256":"da71269e0135798cc79eb61fb142421271afd50c970b477f8865c578ea10a457","abstract_canon_sha256":"d9f8c875dcb503abc543c669b70ea552312f29abe3bf4dd447c0f6ff9e80e2c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:07.148450Z","signature_b64":"Hb2AUi3BT1sG8QOgkRgaew0lnqpj+iLnenqWnV0nyAFOynBAIALUnpqPzqLWN68i+BU8d53VgeQ4HjUAHmvGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"344455c4e217b51c6017c08348d038cff4c8f16b872337dfa49a9c61bd906860","last_reissued_at":"2026-07-05T11:20:07.147906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:07.147906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Multi-Agent Reinforcement Learning for Distributed Channel Access in WLANs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.NI"],"primary_cat":"cs.LG","authors_text":"Chongtao Guo, Geoffrey Ye Li, Jiaming Yu, Le Liang, Shi Jin, Ziyang Guo","submitted_at":"2024-12-18T13:50:31Z","abstract_excerpt":"This paper investigates the use of multi-agent reinforcement learning (MARL) to address distributed channel access in wireless local area networks. In particular, we consider the challenging yet more practical case where the agents heterogeneously adopt value-based or policy-based reinforcement learning algorithms to train the model. We propose a heterogeneous MARL training framework, named QPMIX, which adopts a centralized training with distributed execution paradigm to enable heterogeneous agents to collaborate. Moreover, we theoretically prove the convergence of the proposed heterogeneous M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14218","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/2412.14218/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":"2412.14218","created_at":"2026-07-05T11:20:07.147971+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14218v2","created_at":"2026-07-05T11:20:07.147971+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14218","created_at":"2026-07-05T11:20:07.147971+00:00"},{"alias_kind":"pith_short_12","alias_value":"GRCFLRHCC62R","created_at":"2026-07-05T11:20:07.147971+00:00"},{"alias_kind":"pith_short_16","alias_value":"GRCFLRHCC62RYYAX","created_at":"2026-07-05T11:20:07.147971+00:00"},{"alias_kind":"pith_short_8","alias_value":"GRCFLRHC","created_at":"2026-07-05T11:20:07.147971+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/GRCFLRHCC62RYYAXYCBURUBYZ7","json":"https://pith.science/pith/GRCFLRHCC62RYYAXYCBURUBYZ7.json","graph_json":"https://pith.science/api/pith-number/GRCFLRHCC62RYYAXYCBURUBYZ7/graph.json","events_json":"https://pith.science/api/pith-number/GRCFLRHCC62RYYAXYCBURUBYZ7/events.json","paper":"https://pith.science/paper/GRCFLRHC"},"agent_actions":{"view_html":"https://pith.science/pith/GRCFLRHCC62RYYAXYCBURUBYZ7","download_json":"https://pith.science/pith/GRCFLRHCC62RYYAXYCBURUBYZ7.json","view_paper":"https://pith.science/paper/GRCFLRHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14218&json=true","fetch_graph":"https://pith.science/api/pith-number/GRCFLRHCC62RYYAXYCBURUBYZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/GRCFLRHCC62RYYAXYCBURUBYZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GRCFLRHCC62RYYAXYCBURUBYZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GRCFLRHCC62RYYAXYCBURUBYZ7/action/storage_attestation","attest_author":"https://pith.science/pith/GRCFLRHCC62RYYAXYCBURUBYZ7/action/author_attestation","sign_citation":"https://pith.science/pith/GRCFLRHCC62RYYAXYCBURUBYZ7/action/citation_signature","submit_replication":"https://pith.science/pith/GRCFLRHCC62RYYAXYCBURUBYZ7/action/replication_record"}},"created_at":"2026-07-05T11:20:07.147971+00:00","updated_at":"2026-07-05T11:20:07.147971+00:00"}