{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HDWCLM6ZOGEW5YL342QJGFLU6N","short_pith_number":"pith:HDWCLM6Z","schema_version":"1.0","canonical_sha256":"38ec25b3d971896ee17be6a0931574f37eac014b103fcdb99e8cc17b074b096a","source":{"kind":"arxiv","id":"2204.04687","version":1},"attestation_state":"computed","paper":{"title":"MA-Dreamer: Coordination and communication through shared imagination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Akshay Srinivasan, Kenzo Lobos-Tsunekawa, Michael Spranger","submitted_at":"2022-04-10T13:54:26Z","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"},"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":"2204.04687","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-10T13:54:26Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"c2b23425d2af19dcf76267cee4057975a8fa89fd5d9b0cdfb57db22c23c00467","abstract_canon_sha256":"2c067092ec68caf14358fe60ee1f6d95a498d1397034a6311dd1caa9b8ad9c1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:13:00.571383Z","signature_b64":"v82nOu1zn/ii2n7LlxVbToFJU9TmIvDzRvPta1+i8uIFseAwuKjrU8mGQeLrrfse4+M/+sZa9OLpvmqH9bzvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38ec25b3d971896ee17be6a0931574f37eac014b103fcdb99e8cc17b074b096a","last_reissued_at":"2026-07-05T04:13:00.570948Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:13:00.570948Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MA-Dreamer: Coordination and communication through shared imagination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Akshay Srinivasan, Kenzo Lobos-Tsunekawa, Michael Spranger","submitted_at":"2022-04-10T13:54:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.04687","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/2204.04687/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":"2204.04687","created_at":"2026-07-05T04:13:00.571008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.04687v1","created_at":"2026-07-05T04:13:00.571008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.04687","created_at":"2026-07-05T04:13:00.571008+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDWCLM6ZOGEW","created_at":"2026-07-05T04:13:00.571008+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDWCLM6ZOGEW5YL3","created_at":"2026-07-05T04:13:00.571008+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDWCLM6Z","created_at":"2026-07-05T04:13:00.571008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31361","citing_title":"Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcement Learning","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDWCLM6ZOGEW5YL342QJGFLU6N","json":"https://pith.science/pith/HDWCLM6ZOGEW5YL342QJGFLU6N.json","graph_json":"https://pith.science/api/pith-number/HDWCLM6ZOGEW5YL342QJGFLU6N/graph.json","events_json":"https://pith.science/api/pith-number/HDWCLM6ZOGEW5YL342QJGFLU6N/events.json","paper":"https://pith.science/paper/HDWCLM6Z"},"agent_actions":{"view_html":"https://pith.science/pith/HDWCLM6ZOGEW5YL342QJGFLU6N","download_json":"https://pith.science/pith/HDWCLM6ZOGEW5YL342QJGFLU6N.json","view_paper":"https://pith.science/paper/HDWCLM6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.04687&json=true","fetch_graph":"https://pith.science/api/pith-number/HDWCLM6ZOGEW5YL342QJGFLU6N/graph.json","fetch_events":"https://pith.science/api/pith-number/HDWCLM6ZOGEW5YL342QJGFLU6N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDWCLM6ZOGEW5YL342QJGFLU6N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDWCLM6ZOGEW5YL342QJGFLU6N/action/storage_attestation","attest_author":"https://pith.science/pith/HDWCLM6ZOGEW5YL342QJGFLU6N/action/author_attestation","sign_citation":"https://pith.science/pith/HDWCLM6ZOGEW5YL342QJGFLU6N/action/citation_signature","submit_replication":"https://pith.science/pith/HDWCLM6ZOGEW5YL342QJGFLU6N/action/replication_record"}},"created_at":"2026-07-05T04:13:00.571008+00:00","updated_at":"2026-07-05T04:13:00.571008+00:00"}