{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:OL7RX3MBLWLHIOJ35EUW6IBNXA","short_pith_number":"pith:OL7RX3MB","schema_version":"1.0","canonical_sha256":"72ff1bed815d9674393be9296f202db80b0ff3dd9145f023d12f3ef96eaa7fb9","source":{"kind":"arxiv","id":"2111.11032","version":1},"attestation_state":"computed","paper":{"title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changjie Fan, Chongjie Zhang, Jiamin He, Jianhao Wang, Jiarui Chen, Lulu Zheng, Yang Gao, Yingfeng Chen, Yujing Hu","submitted_at":"2021-11-22T07:34:47Z","abstract_excerpt":"Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the \"induced\" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local action-observation histories, and can capture the interaction between agents due to reward backpropagation during centralized training."},"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":"2111.11032","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T07:34:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"abfd53914c8b9e19920901b4f7e58d2d52367b0056992f9d8a6966791473e28c","abstract_canon_sha256":"07381874d3411b69d626fe7f31e85cc8972c492e2af66bf835308bfe2395233f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:33:59.101944Z","signature_b64":"ie3wKos+0eaShFnV5zdQirkX6iihPXJ67QhbxTvfCVmVIg0P/Nm9F0Q1GvoVSUxuyywqf5D1MNmVS7fBJDs7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72ff1bed815d9674393be9296f202db80b0ff3dd9145f023d12f3ef96eaa7fb9","last_reissued_at":"2026-07-05T03:33:59.101583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:33:59.101583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Changjie Fan, Chongjie Zhang, Jiamin He, Jianhao Wang, Jiarui Chen, Lulu Zheng, Yang Gao, Yingfeng Chen, Yujing Hu","submitted_at":"2021-11-22T07:34:47Z","abstract_excerpt":"Efficient exploration in deep cooperative multi-agent reinforcement learning (MARL) still remains challenging in complex coordination problems. In this paper, we introduce a novel Episodic Multi-agent reinforcement learning with Curiosity-driven exploration, called EMC. We leverage an insight of popular factorized MARL algorithms that the \"induced\" individual Q-values, i.e., the individual utility functions used for local execution, are the embeddings of local action-observation histories, and can capture the interaction between agents due to reward backpropagation during centralized training."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11032","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/2111.11032/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":"2111.11032","created_at":"2026-07-05T03:33:59.101635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.11032v1","created_at":"2026-07-05T03:33:59.101635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11032","created_at":"2026-07-05T03:33:59.101635+00:00"},{"alias_kind":"pith_short_12","alias_value":"OL7RX3MBLWLH","created_at":"2026-07-05T03:33:59.101635+00:00"},{"alias_kind":"pith_short_16","alias_value":"OL7RX3MBLWLHIOJ3","created_at":"2026-07-05T03:33:59.101635+00:00"},{"alias_kind":"pith_short_8","alias_value":"OL7RX3MB","created_at":"2026-07-05T03:33:59.101635+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/OL7RX3MBLWLHIOJ35EUW6IBNXA","json":"https://pith.science/pith/OL7RX3MBLWLHIOJ35EUW6IBNXA.json","graph_json":"https://pith.science/api/pith-number/OL7RX3MBLWLHIOJ35EUW6IBNXA/graph.json","events_json":"https://pith.science/api/pith-number/OL7RX3MBLWLHIOJ35EUW6IBNXA/events.json","paper":"https://pith.science/paper/OL7RX3MB"},"agent_actions":{"view_html":"https://pith.science/pith/OL7RX3MBLWLHIOJ35EUW6IBNXA","download_json":"https://pith.science/pith/OL7RX3MBLWLHIOJ35EUW6IBNXA.json","view_paper":"https://pith.science/paper/OL7RX3MB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.11032&json=true","fetch_graph":"https://pith.science/api/pith-number/OL7RX3MBLWLHIOJ35EUW6IBNXA/graph.json","fetch_events":"https://pith.science/api/pith-number/OL7RX3MBLWLHIOJ35EUW6IBNXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OL7RX3MBLWLHIOJ35EUW6IBNXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OL7RX3MBLWLHIOJ35EUW6IBNXA/action/storage_attestation","attest_author":"https://pith.science/pith/OL7RX3MBLWLHIOJ35EUW6IBNXA/action/author_attestation","sign_citation":"https://pith.science/pith/OL7RX3MBLWLHIOJ35EUW6IBNXA/action/citation_signature","submit_replication":"https://pith.science/pith/OL7RX3MBLWLHIOJ35EUW6IBNXA/action/replication_record"}},"created_at":"2026-07-05T03:33:59.101635+00:00","updated_at":"2026-07-05T03:33:59.101635+00:00"}