{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KNV2I6SCYYZXOC7QPSSFILBXXI","short_pith_number":"pith:KNV2I6SC","schema_version":"1.0","canonical_sha256":"536ba47a42c633770bf07ca4542c37ba11be9ebda8f16132ebee3ee31c551459","source":{"kind":"arxiv","id":"1910.05512","version":1},"attestation_state":"computed","paper":{"title":"Influence-Based Multi-Agent Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Jianhao Wang, Tonghan Wang, Yi Wu","submitted_at":"2019-10-12T07:14:33Z","abstract_excerpt":"Intrinsically motivated reinforcement learning aims to address the exploration challenge for sparse-reward tasks. However, the study of exploration methods in transition-dependent multi-agent settings is largely absent from the literature. We aim to take a step towards solving this problem. We present two exploration methods: exploration via information-theoretic influence (EITI) and exploration via decision-theoretic influence (EDTI), by exploiting the role of interaction in coordinated behaviors of agents. EITI uses mutual information to capture influence transition dynamics. EDTI uses a nov"},"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":"1910.05512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-12T07:14:33Z","cross_cats_sorted":["cs.MA","stat.ML"],"title_canon_sha256":"578158dc4105d0b29b078d5e3aad2ad7697b5d59dff3f0364c906fa95c1476ad","abstract_canon_sha256":"b6d35eef77b75dadf73d3cb0018a34f284a170bbe4f4d6cef6e417cc95363d2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:24.937390Z","signature_b64":"XuhPz2HLTOjbA6H7c54aATlC3T+xlbIcQFSxCh+f6FIMqiSfndCsXikpAgXcXeptCqzoeU9HsVXMtfJGgo4aAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"536ba47a42c633770bf07ca4542c37ba11be9ebda8f16132ebee3ee31c551459","last_reissued_at":"2026-07-05T00:28:24.936905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:24.936905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Influence-Based Multi-Agent Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chongjie Zhang, Jianhao Wang, Tonghan Wang, Yi Wu","submitted_at":"2019-10-12T07:14:33Z","abstract_excerpt":"Intrinsically motivated reinforcement learning aims to address the exploration challenge for sparse-reward tasks. However, the study of exploration methods in transition-dependent multi-agent settings is largely absent from the literature. We aim to take a step towards solving this problem. We present two exploration methods: exploration via information-theoretic influence (EITI) and exploration via decision-theoretic influence (EDTI), by exploiting the role of interaction in coordinated behaviors of agents. EITI uses mutual information to capture influence transition dynamics. EDTI uses a nov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05512","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/1910.05512/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":"1910.05512","created_at":"2026-07-05T00:28:24.936961+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.05512v1","created_at":"2026-07-05T00:28:24.936961+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05512","created_at":"2026-07-05T00:28:24.936961+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNV2I6SCYYZX","created_at":"2026-07-05T00:28:24.936961+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNV2I6SCYYZXOC7Q","created_at":"2026-07-05T00:28:24.936961+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNV2I6SC","created_at":"2026-07-05T00:28:24.936961+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.03506","citing_title":"Optimistic {\\epsilon}-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01049","citing_title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI","json":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI.json","graph_json":"https://pith.science/api/pith-number/KNV2I6SCYYZXOC7QPSSFILBXXI/graph.json","events_json":"https://pith.science/api/pith-number/KNV2I6SCYYZXOC7QPSSFILBXXI/events.json","paper":"https://pith.science/paper/KNV2I6SC"},"agent_actions":{"view_html":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI","download_json":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI.json","view_paper":"https://pith.science/paper/KNV2I6SC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.05512&json=true","fetch_graph":"https://pith.science/api/pith-number/KNV2I6SCYYZXOC7QPSSFILBXXI/graph.json","fetch_events":"https://pith.science/api/pith-number/KNV2I6SCYYZXOC7QPSSFILBXXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/action/storage_attestation","attest_author":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/action/author_attestation","sign_citation":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/action/citation_signature","submit_replication":"https://pith.science/pith/KNV2I6SCYYZXOC7QPSSFILBXXI/action/replication_record"}},"created_at":"2026-07-05T00:28:24.936961+00:00","updated_at":"2026-07-05T00:28:24.936961+00:00"}