{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GHIQPOTFFSQKFYYT2BYIBVBHLV","short_pith_number":"pith:GHIQPOTF","schema_version":"1.0","canonical_sha256":"31d107ba652ca0a2e313d07080d4275d490dfca8ff953b097d82dafb5e2b3b6c","source":{"kind":"arxiv","id":"2306.10715","version":6},"attestation_state":"computed","paper":{"title":"Maximum Entropy Heterogeneous-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Haobo Fu, Jiarong Liu, Qiang Fu, Siyi Hu, Xiaojun Chang, Yaodong Yang, Yifan Zhong","submitted_at":"2023-06-19T06:22:02Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) has been shown effective for cooperative games in recent years. However, existing state-of-the-art methods face challenges related to sample complexity, training instability, and the risk of converging to a suboptimal Nash Equilibrium. In this paper, we propose a unified framework for learning stochastic policies to resolve these issues. We embed cooperative MARL problems into probabilistic graphical models, from which we derive the maximum entropy (MaxEnt) objective for MARL. Based on the MaxEnt framework, we propose Heterogeneous-Agent Soft Actor-Cri"},"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":"2306.10715","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-06-19T06:22:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"abd36ea2e64fdd55899c375c9db2a1807e6bd8ff2b9a7015f87869da453ace2f","abstract_canon_sha256":"5f6a038e042a044d7bfd7524cd30353602faa0df531edfea83a1e00cb38abffd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:00.118045Z","signature_b64":"BakAVDSo1Dfj8jN9fk+XC0ZjV0SAz+LilHROScj6FEXXKHRsdt7av03Yv5VB7D4hCWPrtqOBvcmC39uRzxMDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31d107ba652ca0a2e313d07080d4275d490dfca8ff953b097d82dafb5e2b3b6c","last_reissued_at":"2026-07-05T10:30:00.117460Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:00.117460Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximum Entropy Heterogeneous-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Haobo Fu, Jiarong Liu, Qiang Fu, Siyi Hu, Xiaojun Chang, Yaodong Yang, Yifan Zhong","submitted_at":"2023-06-19T06:22:02Z","abstract_excerpt":"Multi-agent reinforcement learning (MARL) has been shown effective for cooperative games in recent years. However, existing state-of-the-art methods face challenges related to sample complexity, training instability, and the risk of converging to a suboptimal Nash Equilibrium. In this paper, we propose a unified framework for learning stochastic policies to resolve these issues. We embed cooperative MARL problems into probabilistic graphical models, from which we derive the maximum entropy (MaxEnt) objective for MARL. Based on the MaxEnt framework, we propose Heterogeneous-Agent Soft Actor-Cri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10715","kind":"arxiv","version":6},"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/2306.10715/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":"2306.10715","created_at":"2026-07-05T10:30:00.117529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10715v6","created_at":"2026-07-05T10:30:00.117529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10715","created_at":"2026-07-05T10:30:00.117529+00:00"},{"alias_kind":"pith_short_12","alias_value":"GHIQPOTFFSQK","created_at":"2026-07-05T10:30:00.117529+00:00"},{"alias_kind":"pith_short_16","alias_value":"GHIQPOTFFSQKFYYT","created_at":"2026-07-05T10:30:00.117529+00:00"},{"alias_kind":"pith_short_8","alias_value":"GHIQPOTF","created_at":"2026-07-05T10:30:00.117529+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/GHIQPOTFFSQKFYYT2BYIBVBHLV","json":"https://pith.science/pith/GHIQPOTFFSQKFYYT2BYIBVBHLV.json","graph_json":"https://pith.science/api/pith-number/GHIQPOTFFSQKFYYT2BYIBVBHLV/graph.json","events_json":"https://pith.science/api/pith-number/GHIQPOTFFSQKFYYT2BYIBVBHLV/events.json","paper":"https://pith.science/paper/GHIQPOTF"},"agent_actions":{"view_html":"https://pith.science/pith/GHIQPOTFFSQKFYYT2BYIBVBHLV","download_json":"https://pith.science/pith/GHIQPOTFFSQKFYYT2BYIBVBHLV.json","view_paper":"https://pith.science/paper/GHIQPOTF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10715&json=true","fetch_graph":"https://pith.science/api/pith-number/GHIQPOTFFSQKFYYT2BYIBVBHLV/graph.json","fetch_events":"https://pith.science/api/pith-number/GHIQPOTFFSQKFYYT2BYIBVBHLV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GHIQPOTFFSQKFYYT2BYIBVBHLV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GHIQPOTFFSQKFYYT2BYIBVBHLV/action/storage_attestation","attest_author":"https://pith.science/pith/GHIQPOTFFSQKFYYT2BYIBVBHLV/action/author_attestation","sign_citation":"https://pith.science/pith/GHIQPOTFFSQKFYYT2BYIBVBHLV/action/citation_signature","submit_replication":"https://pith.science/pith/GHIQPOTFFSQKFYYT2BYIBVBHLV/action/replication_record"}},"created_at":"2026-07-05T10:30:00.117529+00:00","updated_at":"2026-07-05T10:30:00.117529+00:00"}