{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ARVVR7Z37FUZ7W4YSKXRXWUPNG","short_pith_number":"pith:ARVVR7Z3","schema_version":"1.0","canonical_sha256":"046b58ff3bf9699fdb9892af1bda8f69a8437bc813c23687042b065cccb9d2be","source":{"kind":"arxiv","id":"2501.11818","version":2},"attestation_state":"computed","paper":{"title":"Group-Agent Reinforcement Learning with Heterogeneous Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaiyue Wu, Tingting Mu, Xiao-Jun Zeng","submitted_at":"2025-01-21T01:56:33Z","abstract_excerpt":"Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function"},"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":"2501.11818","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-21T01:56:33Z","cross_cats_sorted":[],"title_canon_sha256":"1dedfedba28d340ade2dec8e1b16d87831a7a07223ba37f6a8072fd3d00f5599","abstract_canon_sha256":"7e08799c2911291b2bcc30d43fd01d022de577116b4a0003c1510d207992c79f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:49.977937Z","signature_b64":"I2fqx8keaExpEl6rHDk6md9QgM75TYlEQm+9E85KOniYZFNbJX9h021le3qYSRtRrZScIBHcn3jYhN5M6uv0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"046b58ff3bf9699fdb9892af1bda8f69a8437bc813c23687042b065cccb9d2be","last_reissued_at":"2026-07-05T10:14:49.977385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:49.977385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group-Agent Reinforcement Learning with Heterogeneous Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kaiyue Wu, Tingting Mu, Xiao-Jun Zeng","submitted_at":"2025-01-21T01:56:33Z","abstract_excerpt":"Group-agent reinforcement learning (GARL) is a newly arising learning scenario, where multiple reinforcement learning agents study together in a group, sharing knowledge in an asynchronous fashion. The goal is to improve the learning performance of each individual agent. Under a more general heterogeneous setting where different agents learn using different algorithms, we advance GARL by designing novel and effective group-learning mechanisms. They guide the agents on whether and how to learn from action choices from the others, and allow the agents to adopt available policy and value function"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11818","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/2501.11818/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":"2501.11818","created_at":"2026-07-05T10:14:49.977461+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11818v2","created_at":"2026-07-05T10:14:49.977461+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11818","created_at":"2026-07-05T10:14:49.977461+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARVVR7Z37FUZ","created_at":"2026-07-05T10:14:49.977461+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARVVR7Z37FUZ7W4Y","created_at":"2026-07-05T10:14:49.977461+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARVVR7Z3","created_at":"2026-07-05T10:14:49.977461+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/ARVVR7Z37FUZ7W4YSKXRXWUPNG","json":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG.json","graph_json":"https://pith.science/api/pith-number/ARVVR7Z37FUZ7W4YSKXRXWUPNG/graph.json","events_json":"https://pith.science/api/pith-number/ARVVR7Z37FUZ7W4YSKXRXWUPNG/events.json","paper":"https://pith.science/paper/ARVVR7Z3"},"agent_actions":{"view_html":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG","download_json":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG.json","view_paper":"https://pith.science/paper/ARVVR7Z3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11818&json=true","fetch_graph":"https://pith.science/api/pith-number/ARVVR7Z37FUZ7W4YSKXRXWUPNG/graph.json","fetch_events":"https://pith.science/api/pith-number/ARVVR7Z37FUZ7W4YSKXRXWUPNG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/action/storage_attestation","attest_author":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/action/author_attestation","sign_citation":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/action/citation_signature","submit_replication":"https://pith.science/pith/ARVVR7Z37FUZ7W4YSKXRXWUPNG/action/replication_record"}},"created_at":"2026-07-05T10:14:49.977461+00:00","updated_at":"2026-07-05T10:14:49.977461+00:00"}