{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YMOTNQOS5BDGZBDCC7QDU3XWAR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"00ac111403483d40215740ea0b23df4b7ecb88ab427c6a42319616bed37b8616","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T14:49:26Z","title_canon_sha256":"9e4677b068a16224f5b7bca8db5b1dceb315f9952b670f35c2bb52a18b5aad54"},"schema_version":"1.0","source":{"id":"2505.08630","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08630","created_at":"2026-07-05T11:02:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08630v1","created_at":"2026-07-05T11:02:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08630","created_at":"2026-07-05T11:02:33Z"},{"alias_kind":"pith_short_12","alias_value":"YMOTNQOS5BDG","created_at":"2026-07-05T11:02:33Z"},{"alias_kind":"pith_short_16","alias_value":"YMOTNQOS5BDGZBDC","created_at":"2026-07-05T11:02:33Z"},{"alias_kind":"pith_short_8","alias_value":"YMOTNQOS","created_at":"2026-07-05T11:02:33Z"}],"graph_snapshots":[{"event_id":"sha256:f1f5b03bd40e3e156570c65d2ffa2df0214c9fd0b3fa16cb88d5599e8e9e810c","target":"graph","created_at":"2026-07-05T11:02:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.08630/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Mehdi Dastani, Shihan Wang, Shuai Han","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T14:49:26Z","title":"Credit Assignment and Efficient Exploration based on Influence Scope in Multi-agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08630","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b7d87343592b2f5d29274b87eb1e4fc54ad82872702e47bba3550f28577b37aa","target":"record","created_at":"2026-07-05T11:02:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"00ac111403483d40215740ea0b23df4b7ecb88ab427c6a42319616bed37b8616","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-13T14:49:26Z","title_canon_sha256":"9e4677b068a16224f5b7bca8db5b1dceb315f9952b670f35c2bb52a18b5aad54"},"schema_version":"1.0","source":{"id":"2505.08630","kind":"arxiv","version":1}},"canonical_sha256":"c31d36c1d2e8466c846217e03a6ef604663b2874fd278bdf534e9acb67af3d49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c31d36c1d2e8466c846217e03a6ef604663b2874fd278bdf534e9acb67af3d49","first_computed_at":"2026-07-05T11:02:33.819954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:02:33.819954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zXZkqlXhoHesH3s/Fob+kUbB13TC1cKtvjplLQzeMi31SsFPhPvQDOSXEa5wlACELPRTi/a6zUnRfEQFVa4ABA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:02:33.820521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08630","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7d87343592b2f5d29274b87eb1e4fc54ad82872702e47bba3550f28577b37aa","sha256:f1f5b03bd40e3e156570c65d2ffa2df0214c9fd0b3fa16cb88d5599e8e9e810c"],"state_sha256":"61afd7e05636c66eff57db14508ab7d86b9c14c77a420735b3f47abe6b6fb997"}