{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:R5SWHLUZG6F3OHJKAUMU7R45DI","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":"25e2cd45c8d57d40855249023852ce2df5db85a9ad2ee6d336c6acab3ab7ebd7","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T23:01:02Z","title_canon_sha256":"d4bc12571e3ca578d0ef718248405c0419829b00226147cbf44f798473d95bee"},"schema_version":"1.0","source":{"id":"1905.12127","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.12127","created_at":"2026-07-05T02:42:24Z"},{"alias_kind":"arxiv_version","alias_value":"1905.12127v3","created_at":"2026-07-05T02:42:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12127","created_at":"2026-07-05T02:42:24Z"},{"alias_kind":"pith_short_12","alias_value":"R5SWHLUZG6F3","created_at":"2026-07-05T02:42:24Z"},{"alias_kind":"pith_short_16","alias_value":"R5SWHLUZG6F3OHJK","created_at":"2026-07-05T02:42:24Z"},{"alias_kind":"pith_short_8","alias_value":"R5SWHLUZ","created_at":"2026-07-05T02:42:24Z"}],"graph_snapshots":[{"event_id":"sha256:f72f3012cc7463fa88fe0c8853bfb126a79fa7b9768b169a2ffb3f29a019602b","target":"graph","created_at":"2026-07-05T02:42:24Z","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/1905.12127/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Solving tasks with sparse rewards is one of the most important challenges in reinforcement learning. In the single-agent setting, this challenge is addressed by introducing intrinsic rewards that motivate agents to explore unseen regions of their state spaces; however, applying these techniques naively to the multi-agent setting results in agents exploring independently, without any coordination among themselves. Exploration in cooperative multi-agent settings can be accelerated and improved if agents coordinate their exploration. In this paper we introduce a framework for designing intrinsic ","authors_text":"Fei Sha, Shariq Iqbal","cross_cats":["cs.AI","cs.MA","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T23:01:02Z","title":"Coordinated Exploration via Intrinsic Rewards for Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12127","kind":"arxiv","version":3},"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:c716b1cf305f845c0bbdf3dc5b0b08cc50429a81b112c9d0317dfcfc8330b1ec","target":"record","created_at":"2026-07-05T02:42:24Z","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":"25e2cd45c8d57d40855249023852ce2df5db85a9ad2ee6d336c6acab3ab7ebd7","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-28T23:01:02Z","title_canon_sha256":"d4bc12571e3ca578d0ef718248405c0419829b00226147cbf44f798473d95bee"},"schema_version":"1.0","source":{"id":"1905.12127","kind":"arxiv","version":3}},"canonical_sha256":"8f6563ae99378bb71d2a05194fc79d1a37c037dfe0107376dfde871a72ddf777","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f6563ae99378bb71d2a05194fc79d1a37c037dfe0107376dfde871a72ddf777","first_computed_at":"2026-07-05T02:42:24.222257Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:24.222257Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M4Jzl6sfmP78e69oj4u8D3qXAjFNUFjwrYMHigBa09pwV3jGpO35UFQ2HyER/ktB37ox1Sg8bn76U1twErn0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:24.222766Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.12127","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c716b1cf305f845c0bbdf3dc5b0b08cc50429a81b112c9d0317dfcfc8330b1ec","sha256:f72f3012cc7463fa88fe0c8853bfb126a79fa7b9768b169a2ffb3f29a019602b"],"state_sha256":"937fd7652acf5fbdcafd6ead23e0b4565a7718012c067352fe7ef0d1a7f9ca56"}