{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:K2NF4WJRBVA4ZWJT4Y3AVN7VHS","short_pith_number":"pith:K2NF4WJR","schema_version":"1.0","canonical_sha256":"569a5e59310d41ccd933e6360ab7f53c94c7ca00425b29e5c675ce13f6238484","source":{"kind":"arxiv","id":"2310.07218","version":1},"attestation_state":"computed","paper":{"title":"Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Chenran Li, Chen Tang, Jinning Li, Masayoshi Tomizuka, Ran Tian, Wei Zhan, Yuxin Chen","submitted_at":"2023-10-11T06:09:26Z","abstract_excerpt":"Generalization poses a significant challenge in Multi-agent Reinforcement Learning (MARL). The extent to which an agent is influenced by unseen co-players depends on the agent's policy and the specific scenario. A quantitative examination of this relationship sheds light on effectively training agents for diverse scenarios. In this study, we present the Level of Influence (LoI), a metric quantifying the interaction intensity among agents within a given scenario and environment. We observe that, generally, a more diverse set of co-play agents during training enhances the generalization performa"},"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":"2310.07218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2023-10-11T06:09:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e0da6b01de6e3ad87d6462d2b447c9a9efe5cd365d4d91f0853f08424c2e9c27","abstract_canon_sha256":"5675cc45ae5a4e40ad64e7091440118e68a66c9cbe1498f76acadcc235146698"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:42.266592Z","signature_b64":"Sww2XMTjGPqPM8joTqGsRuO2/LEMYJjL1FdBs4ppSvbJs/vx6r3yo1H0kwZxLNxMg+HJLC+Mm3it5fn9mlHCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"569a5e59310d41ccd933e6360ab7f53c94c7ca00425b29e5c675ce13f6238484","last_reissued_at":"2026-07-05T06:59:42.266159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:42.266159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantifying Agent Interaction in Multi-agent Reinforcement Learning for Cost-efficient Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Chenran Li, Chen Tang, Jinning Li, Masayoshi Tomizuka, Ran Tian, Wei Zhan, Yuxin Chen","submitted_at":"2023-10-11T06:09:26Z","abstract_excerpt":"Generalization poses a significant challenge in Multi-agent Reinforcement Learning (MARL). The extent to which an agent is influenced by unseen co-players depends on the agent's policy and the specific scenario. A quantitative examination of this relationship sheds light on effectively training agents for diverse scenarios. In this study, we present the Level of Influence (LoI), a metric quantifying the interaction intensity among agents within a given scenario and environment. We observe that, generally, a more diverse set of co-play agents during training enhances the generalization performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07218","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/2310.07218/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":"2310.07218","created_at":"2026-07-05T06:59:42.266212+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07218v1","created_at":"2026-07-05T06:59:42.266212+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07218","created_at":"2026-07-05T06:59:42.266212+00:00"},{"alias_kind":"pith_short_12","alias_value":"K2NF4WJRBVA4","created_at":"2026-07-05T06:59:42.266212+00:00"},{"alias_kind":"pith_short_16","alias_value":"K2NF4WJRBVA4ZWJT","created_at":"2026-07-05T06:59:42.266212+00:00"},{"alias_kind":"pith_short_8","alias_value":"K2NF4WJR","created_at":"2026-07-05T06:59:42.266212+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.12714","citing_title":"Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/K2NF4WJRBVA4ZWJT4Y3AVN7VHS","json":"https://pith.science/pith/K2NF4WJRBVA4ZWJT4Y3AVN7VHS.json","graph_json":"https://pith.science/api/pith-number/K2NF4WJRBVA4ZWJT4Y3AVN7VHS/graph.json","events_json":"https://pith.science/api/pith-number/K2NF4WJRBVA4ZWJT4Y3AVN7VHS/events.json","paper":"https://pith.science/paper/K2NF4WJR"},"agent_actions":{"view_html":"https://pith.science/pith/K2NF4WJRBVA4ZWJT4Y3AVN7VHS","download_json":"https://pith.science/pith/K2NF4WJRBVA4ZWJT4Y3AVN7VHS.json","view_paper":"https://pith.science/paper/K2NF4WJR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07218&json=true","fetch_graph":"https://pith.science/api/pith-number/K2NF4WJRBVA4ZWJT4Y3AVN7VHS/graph.json","fetch_events":"https://pith.science/api/pith-number/K2NF4WJRBVA4ZWJT4Y3AVN7VHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/K2NF4WJRBVA4ZWJT4Y3AVN7VHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/K2NF4WJRBVA4ZWJT4Y3AVN7VHS/action/storage_attestation","attest_author":"https://pith.science/pith/K2NF4WJRBVA4ZWJT4Y3AVN7VHS/action/author_attestation","sign_citation":"https://pith.science/pith/K2NF4WJRBVA4ZWJT4Y3AVN7VHS/action/citation_signature","submit_replication":"https://pith.science/pith/K2NF4WJRBVA4ZWJT4Y3AVN7VHS/action/replication_record"}},"created_at":"2026-07-05T06:59:42.266212+00:00","updated_at":"2026-07-05T06:59:42.266212+00:00"}