{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:K7FXKX6B3CYJBCCMACGVELJN2L","short_pith_number":"pith:K7FXKX6B","schema_version":"1.0","canonical_sha256":"57cb755fc1d8b090884c008d522d2dd2d50e7a62ec5413cb6c6db1bcf4ecaa3c","source":{"kind":"arxiv","id":"2112.08702","version":2},"attestation_state":"computed","paper":{"title":"Learning to Share in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Ge Li, Yaowei Wang, Yuxuan Yi, Zongqing Lu","submitted_at":"2021-12-16T08:43:20Z","abstract_excerpt":"In this paper, we study the problem of networked multi-agent reinforcement learning (MARL), where a number of agents are deployed as a partially connected network and each interacts only with nearby agents. Networked MARL requires all agents to make decisions in a decentralized manner to optimize a global objective with restricted communication between neighbors over the network. Inspired by the fact that sharing plays a key role in human's learning of cooperation, we propose LToS, a hierarchically decentralized MARL framework that enables agents to learn to dynamically share reward with neigh"},"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":"2112.08702","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-16T08:43:20Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"0df3255cc8aec1b468ccd81ba47255a26e3182b85ed8ce4cadb0d68aa50a9cd2","abstract_canon_sha256":"bb63e958b6c344e17d251059704db0fae57f5b9e97e1356c90b72e5de63602d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:27.667428Z","signature_b64":"gQ4lwJoU4TeM1UalgnhqkYE4B0I3TLhw5NgPr5cC7mLmTnJOVbvYgzo3XE2l6h7xS8ErMAjpYg043TbQi4rhDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"57cb755fc1d8b090884c008d522d2dd2d50e7a62ec5413cb6c6db1bcf4ecaa3c","last_reissued_at":"2026-07-05T04:33:27.666969Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:27.666969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Share in Multi-Agent Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Ge Li, Yaowei Wang, Yuxuan Yi, Zongqing Lu","submitted_at":"2021-12-16T08:43:20Z","abstract_excerpt":"In this paper, we study the problem of networked multi-agent reinforcement learning (MARL), where a number of agents are deployed as a partially connected network and each interacts only with nearby agents. Networked MARL requires all agents to make decisions in a decentralized manner to optimize a global objective with restricted communication between neighbors over the network. Inspired by the fact that sharing plays a key role in human's learning of cooperation, we propose LToS, a hierarchically decentralized MARL framework that enables agents to learn to dynamically share reward with neigh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.08702","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/2112.08702/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":"2112.08702","created_at":"2026-07-05T04:33:27.667044+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.08702v2","created_at":"2026-07-05T04:33:27.667044+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.08702","created_at":"2026-07-05T04:33:27.667044+00:00"},{"alias_kind":"pith_short_12","alias_value":"K7FXKX6B3CYJ","created_at":"2026-07-05T04:33:27.667044+00:00"},{"alias_kind":"pith_short_16","alias_value":"K7FXKX6B3CYJBCCM","created_at":"2026-07-05T04:33:27.667044+00:00"},{"alias_kind":"pith_short_8","alias_value":"K7FXKX6B","created_at":"2026-07-05T04:33:27.667044+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.12326","citing_title":"Achieving Collective Welfare in Multi-Agent Reinforcement Learning via Suggestion Sharing","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K7FXKX6B3CYJBCCMACGVELJN2L","json":"https://pith.science/pith/K7FXKX6B3CYJBCCMACGVELJN2L.json","graph_json":"https://pith.science/api/pith-number/K7FXKX6B3CYJBCCMACGVELJN2L/graph.json","events_json":"https://pith.science/api/pith-number/K7FXKX6B3CYJBCCMACGVELJN2L/events.json","paper":"https://pith.science/paper/K7FXKX6B"},"agent_actions":{"view_html":"https://pith.science/pith/K7FXKX6B3CYJBCCMACGVELJN2L","download_json":"https://pith.science/pith/K7FXKX6B3CYJBCCMACGVELJN2L.json","view_paper":"https://pith.science/paper/K7FXKX6B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.08702&json=true","fetch_graph":"https://pith.science/api/pith-number/K7FXKX6B3CYJBCCMACGVELJN2L/graph.json","fetch_events":"https://pith.science/api/pith-number/K7FXKX6B3CYJBCCMACGVELJN2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K7FXKX6B3CYJBCCMACGVELJN2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K7FXKX6B3CYJBCCMACGVELJN2L/action/storage_attestation","attest_author":"https://pith.science/pith/K7FXKX6B3CYJBCCMACGVELJN2L/action/author_attestation","sign_citation":"https://pith.science/pith/K7FXKX6B3CYJBCCMACGVELJN2L/action/citation_signature","submit_replication":"https://pith.science/pith/K7FXKX6B3CYJBCCMACGVELJN2L/action/replication_record"}},"created_at":"2026-07-05T04:33:27.667044+00:00","updated_at":"2026-07-05T04:33:27.667044+00:00"}