{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YMOTNQOS5BDGZBDCC7QDU3XWAR","short_pith_number":"pith:YMOTNQOS","schema_version":"1.0","canonical_sha256":"c31d36c1d2e8466c846217e03a6ef604663b2874fd278bdf534e9acb67af3d49","source":{"kind":"arxiv","id":"2505.08630","version":1},"attestation_state":"computed","paper":{"title":"Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mehdi Dastani, Shihan Wang, Shuai Han","submitted_at":"2025-05-13T14:49:26Z","abstract_excerpt":"Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL). Without clear feedback on actions at each step in sparse-reward setting, previous methods struggle with precise credit assignment among agents and effective exploration. In this paper, we introduce a novel method to deal with both credit assignment and exploration problems in reward-sparse domains. Accordingly, we propose an algorithm that calculates the Influence Scope of Agents (ISA) on states by taking specific value of the dimensions/attributes of states that c"},"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":"2505.08630","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T14:49:26Z","cross_cats_sorted":[],"title_canon_sha256":"9e4677b068a16224f5b7bca8db5b1dceb315f9952b670f35c2bb52a18b5aad54","abstract_canon_sha256":"00ac111403483d40215740ea0b23df4b7ecb88ab427c6a42319616bed37b8616"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:33.820521Z","signature_b64":"zXZkqlXhoHesH3s/Fob+kUbB13TC1cKtvjplLQzeMi31SsFPhPvQDOSXEa5wlACELPRTi/a6zUnRfEQFVa4ABA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c31d36c1d2e8466c846217e03a6ef604663b2874fd278bdf534e9acb67af3d49","last_reissued_at":"2026-07-05T11:02:33.819954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:33.819954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mehdi Dastani, Shihan Wang, Shuai Han","submitted_at":"2025-05-13T14:49:26Z","abstract_excerpt":"Training cooperative agents in sparse-reward scenarios poses significant challenges for multi-agent reinforcement learning (MARL). Without clear feedback on actions at each step in sparse-reward setting, previous methods struggle with precise credit assignment among agents and effective exploration. In this paper, we introduce a novel method to deal with both credit assignment and exploration problems in reward-sparse domains. Accordingly, we propose an algorithm that calculates the Influence Scope of Agents (ISA) on states by taking specific value of the dimensions/attributes of states that c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08630","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/2505.08630/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":"2505.08630","created_at":"2026-07-05T11:02:33.820012+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.08630v1","created_at":"2026-07-05T11:02:33.820012+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08630","created_at":"2026-07-05T11:02:33.820012+00:00"},{"alias_kind":"pith_short_12","alias_value":"YMOTNQOS5BDG","created_at":"2026-07-05T11:02:33.820012+00:00"},{"alias_kind":"pith_short_16","alias_value":"YMOTNQOS5BDGZBDC","created_at":"2026-07-05T11:02:33.820012+00:00"},{"alias_kind":"pith_short_8","alias_value":"YMOTNQOS","created_at":"2026-07-05T11:02:33.820012+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/YMOTNQOS5BDGZBDCC7QDU3XWAR","json":"https://pith.science/pith/YMOTNQOS5BDGZBDCC7QDU3XWAR.json","graph_json":"https://pith.science/api/pith-number/YMOTNQOS5BDGZBDCC7QDU3XWAR/graph.json","events_json":"https://pith.science/api/pith-number/YMOTNQOS5BDGZBDCC7QDU3XWAR/events.json","paper":"https://pith.science/paper/YMOTNQOS"},"agent_actions":{"view_html":"https://pith.science/pith/YMOTNQOS5BDGZBDCC7QDU3XWAR","download_json":"https://pith.science/pith/YMOTNQOS5BDGZBDCC7QDU3XWAR.json","view_paper":"https://pith.science/paper/YMOTNQOS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.08630&json=true","fetch_graph":"https://pith.science/api/pith-number/YMOTNQOS5BDGZBDCC7QDU3XWAR/graph.json","fetch_events":"https://pith.science/api/pith-number/YMOTNQOS5BDGZBDCC7QDU3XWAR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YMOTNQOS5BDGZBDCC7QDU3XWAR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YMOTNQOS5BDGZBDCC7QDU3XWAR/action/storage_attestation","attest_author":"https://pith.science/pith/YMOTNQOS5BDGZBDCC7QDU3XWAR/action/author_attestation","sign_citation":"https://pith.science/pith/YMOTNQOS5BDGZBDCC7QDU3XWAR/action/citation_signature","submit_replication":"https://pith.science/pith/YMOTNQOS5BDGZBDCC7QDU3XWAR/action/replication_record"}},"created_at":"2026-07-05T11:02:33.820012+00:00","updated_at":"2026-07-05T11:02:33.820012+00:00"}