{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XZRHKSZSQBEXKKDBC7P5NIBQAF","short_pith_number":"pith:XZRHKSZS","schema_version":"1.0","canonical_sha256":"be62754b32804975286117dfd6a0300155d21b589e8c12e180178d0cbb89b394","source":{"kind":"arxiv","id":"2508.10423","version":1},"attestation_state":"computed","paper":{"title":"MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jinliang Ding, Mingshan Tan, Qi Liu, Shuaikang Ma, Xiaopeng Zhang, Yanjie Li","submitted_at":"2025-08-14T07:54:31Z","abstract_excerpt":"This paper proposes a novel method to enhance locomotion for a single humanoid robot through cooperative-heterogeneous multi-agent deep reinforcement learning (MARL). While most existing methods typically employ single-agent reinforcement learning algorithms for a single humanoid robot or MARL algorithms for multi-robot system tasks, we propose a distinct paradigm: applying cooperative-heterogeneous MARL to optimize locomotion for a single humanoid robot. The proposed method, multi-agent reinforcement learning for single humanoid locomotion (MASH), treats each limb (legs and arms) as an indepe"},"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":"2508.10423","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-08-14T07:54:31Z","cross_cats_sorted":["cs.AI","cs.SY","eess.SY"],"title_canon_sha256":"f0f5afae69179c2994f344df8febf4a41efe00879eaa0941d9097002c3307a7f","abstract_canon_sha256":"46eeb60b828c9a1e94a7dc8c67aa05b77bc6f0cee54e65fbd44d42e15b8639d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:55.912521Z","signature_b64":"1c0WitNuiUeyCjx560+26EI3X4Ks+M4LfoL/Gq2WP2NCxaL1l4KSZtINh3OllVK+pLUMItn1rySvOdqA/ErGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be62754b32804975286117dfd6a0300155d21b589e8c12e180178d0cbb89b394","last_reissued_at":"2026-07-05T11:53:55.912079Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:55.912079Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MASH: Cooperative-Heterogeneous Multi-Agent Reinforcement Learning for Single Humanoid Robot Locomotion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jinliang Ding, Mingshan Tan, Qi Liu, Shuaikang Ma, Xiaopeng Zhang, Yanjie Li","submitted_at":"2025-08-14T07:54:31Z","abstract_excerpt":"This paper proposes a novel method to enhance locomotion for a single humanoid robot through cooperative-heterogeneous multi-agent deep reinforcement learning (MARL). While most existing methods typically employ single-agent reinforcement learning algorithms for a single humanoid robot or MARL algorithms for multi-robot system tasks, we propose a distinct paradigm: applying cooperative-heterogeneous MARL to optimize locomotion for a single humanoid robot. The proposed method, multi-agent reinforcement learning for single humanoid locomotion (MASH), treats each limb (legs and arms) as an indepe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10423","kind":"arxiv","version":1},"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/2508.10423/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":"2508.10423","created_at":"2026-07-05T11:53:55.912128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10423v1","created_at":"2026-07-05T11:53:55.912128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10423","created_at":"2026-07-05T11:53:55.912128+00:00"},{"alias_kind":"pith_short_12","alias_value":"XZRHKSZSQBEX","created_at":"2026-07-05T11:53:55.912128+00:00"},{"alias_kind":"pith_short_16","alias_value":"XZRHKSZSQBEXKKDB","created_at":"2026-07-05T11:53:55.912128+00:00"},{"alias_kind":"pith_short_8","alias_value":"XZRHKSZS","created_at":"2026-07-05T11:53:55.912128+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/XZRHKSZSQBEXKKDBC7P5NIBQAF","json":"https://pith.science/pith/XZRHKSZSQBEXKKDBC7P5NIBQAF.json","graph_json":"https://pith.science/api/pith-number/XZRHKSZSQBEXKKDBC7P5NIBQAF/graph.json","events_json":"https://pith.science/api/pith-number/XZRHKSZSQBEXKKDBC7P5NIBQAF/events.json","paper":"https://pith.science/paper/XZRHKSZS"},"agent_actions":{"view_html":"https://pith.science/pith/XZRHKSZSQBEXKKDBC7P5NIBQAF","download_json":"https://pith.science/pith/XZRHKSZSQBEXKKDBC7P5NIBQAF.json","view_paper":"https://pith.science/paper/XZRHKSZS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10423&json=true","fetch_graph":"https://pith.science/api/pith-number/XZRHKSZSQBEXKKDBC7P5NIBQAF/graph.json","fetch_events":"https://pith.science/api/pith-number/XZRHKSZSQBEXKKDBC7P5NIBQAF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XZRHKSZSQBEXKKDBC7P5NIBQAF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XZRHKSZSQBEXKKDBC7P5NIBQAF/action/storage_attestation","attest_author":"https://pith.science/pith/XZRHKSZSQBEXKKDBC7P5NIBQAF/action/author_attestation","sign_citation":"https://pith.science/pith/XZRHKSZSQBEXKKDBC7P5NIBQAF/action/citation_signature","submit_replication":"https://pith.science/pith/XZRHKSZSQBEXKKDBC7P5NIBQAF/action/replication_record"}},"created_at":"2026-07-05T11:53:55.912128+00:00","updated_at":"2026-07-05T11:53:55.912128+00:00"}