{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:OL7RX3MBLWLHIOJ35EUW6IBNXA","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":"07381874d3411b69d626fe7f31e85cc8972c492e2af66bf835308bfe2395233f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T07:34:47Z","title_canon_sha256":"abfd53914c8b9e19920901b4f7e58d2d52367b0056992f9d8a6966791473e28c"},"schema_version":"1.0","source":{"id":"2111.11032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.11032","created_at":"2026-07-05T03:33:59Z"},{"alias_kind":"arxiv_version","alias_value":"2111.11032v1","created_at":"2026-07-05T03:33:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.11032","created_at":"2026-07-05T03:33:59Z"},{"alias_kind":"pith_short_12","alias_value":"OL7RX3MBLWLH","created_at":"2026-07-05T03:33:59Z"},{"alias_kind":"pith_short_16","alias_value":"OL7RX3MBLWLHIOJ3","created_at":"2026-07-05T03:33:59Z"},{"alias_kind":"pith_short_8","alias_value":"OL7RX3MB","created_at":"2026-07-05T03:33:59Z"}],"graph_snapshots":[{"event_id":"sha256:c41ef2fc4cd5028763bfadba5655fc48886a948d55c728c4c5d319887e78d739","target":"graph","created_at":"2026-07-05T03:33:59Z","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/2111.11032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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.","authors_text":"Changjie Fan, Chongjie Zhang, Jiamin He, Jianhao Wang, Jiarui Chen, Lulu Zheng, Yang Gao, Yingfeng Chen, Yujing Hu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T07:34:47Z","title":"Episodic Multi-agent Reinforcement Learning with Curiosity-Driven Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.11032","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:f9f1e3b50d389acb637545d84505c43c63d450c2b8bf4376281f59372cd91351","target":"record","created_at":"2026-07-05T03:33:59Z","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":"07381874d3411b69d626fe7f31e85cc8972c492e2af66bf835308bfe2395233f","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-22T07:34:47Z","title_canon_sha256":"abfd53914c8b9e19920901b4f7e58d2d52367b0056992f9d8a6966791473e28c"},"schema_version":"1.0","source":{"id":"2111.11032","kind":"arxiv","version":1}},"canonical_sha256":"72ff1bed815d9674393be9296f202db80b0ff3dd9145f023d12f3ef96eaa7fb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72ff1bed815d9674393be9296f202db80b0ff3dd9145f023d12f3ef96eaa7fb9","first_computed_at":"2026-07-05T03:33:59.101583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:33:59.101583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ie3wKos+0eaShFnV5zdQirkX6iihPXJ67QhbxTvfCVmVIg0P/Nm9F0Q1GvoVSUxuyywqf5D1MNmVS7fBJDs7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:33:59.101944Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.11032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f9f1e3b50d389acb637545d84505c43c63d450c2b8bf4376281f59372cd91351","sha256:c41ef2fc4cd5028763bfadba5655fc48886a948d55c728c4c5d319887e78d739"],"state_sha256":"33e5eb792d7086066a7ef85b32fce4265625cc08c9fe50ca42f315f2f2f48224"}