{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HDWCLM6ZOGEW5YL342QJGFLU6N","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":"2c067092ec68caf14358fe60ee1f6d95a498d1397034a6311dd1caa9b8ad9c1b","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-10T13:54:26Z","title_canon_sha256":"c2b23425d2af19dcf76267cee4057975a8fa89fd5d9b0cdfb57db22c23c00467"},"schema_version":"1.0","source":{"id":"2204.04687","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.04687","created_at":"2026-07-05T04:13:00Z"},{"alias_kind":"arxiv_version","alias_value":"2204.04687v1","created_at":"2026-07-05T04:13:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04687","created_at":"2026-07-05T04:13:00Z"},{"alias_kind":"pith_short_12","alias_value":"HDWCLM6ZOGEW","created_at":"2026-07-05T04:13:00Z"},{"alias_kind":"pith_short_16","alias_value":"HDWCLM6ZOGEW5YL3","created_at":"2026-07-05T04:13:00Z"},{"alias_kind":"pith_short_8","alias_value":"HDWCLM6Z","created_at":"2026-07-05T04:13:00Z"}],"graph_snapshots":[{"event_id":"sha256:233961a9b217bf7c9e41a05c9604d91dc10557d7861f31fc4134a9c664e76515","target":"graph","created_at":"2026-07-05T04:13:00Z","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/2204.04687/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent RL is rendered difficult due to the non-stationary nature of environment perceived by individual agents. Theoretically sound methods using the REINFORCE estimator are impeded by its high-variance, whereas value-function based methods are affected by issues stemming from their ad-hoc handling of situations like inter-agent communication. Methods like MADDPG are further constrained due to their requirement of centralized critics etc. In order to address these issues, we present MA-Dreamer, a model-based method that uses both agent-centric and global differentiable models of the envir","authors_text":"Akshay Srinivasan, Kenzo Lobos-Tsunekawa, Michael Spranger","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-10T13:54:26Z","title":"MA-Dreamer: Coordination and communication through shared imagination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04687","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":"sha256:4e74f65d5f630e599117f4908710bba918bbcea9b3e9389e28dd176154e5ee1e","target":"record","created_at":"2026-07-05T04:13:00Z","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":"2c067092ec68caf14358fe60ee1f6d95a498d1397034a6311dd1caa9b8ad9c1b","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-10T13:54:26Z","title_canon_sha256":"c2b23425d2af19dcf76267cee4057975a8fa89fd5d9b0cdfb57db22c23c00467"},"schema_version":"1.0","source":{"id":"2204.04687","kind":"arxiv","version":1}},"canonical_sha256":"38ec25b3d971896ee17be6a0931574f37eac014b103fcdb99e8cc17b074b096a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38ec25b3d971896ee17be6a0931574f37eac014b103fcdb99e8cc17b074b096a","first_computed_at":"2026-07-05T04:13:00.570948Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:13:00.570948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v82nOu1zn/ii2n7LlxVbToFJU9TmIvDzRvPta1+i8uIFseAwuKjrU8mGQeLrrfse4+M/+sZa9OLpvmqH9bzvBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:13:00.571383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.04687","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e74f65d5f630e599117f4908710bba918bbcea9b3e9389e28dd176154e5ee1e","sha256:233961a9b217bf7c9e41a05c9604d91dc10557d7861f31fc4134a9c664e76515"],"state_sha256":"26ddd6d70db9e86280a5d72749373d376d8f5e56db13d3e658f568f1389b3cac"}