{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GUQZ244CZX5O7FUSCRDZD2RWX4","short_pith_number":"pith:GUQZ244C","schema_version":"1.0","canonical_sha256":"35219d7382cdfaef9692144791ea36bf3d1d7ef1262344d0e9f958d4c79beee0","source":{"kind":"arxiv","id":"2406.13600","version":1},"attestation_state":"computed","paper":{"title":"CoDreamer: Communication-Based Decentralised World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amanda Prorok, Edan Toledo","submitted_at":"2024-06-19T14:42:40Z","abstract_excerpt":"Sample efficiency is a critical challenge in reinforcement learning. Model-based RL has emerged as a solution, but its application has largely been confined to single-agent scenarios. In this work, we introduce CoDreamer, an extension of the Dreamer algorithm for multi-agent environments. CoDreamer leverages Graph Neural Networks for a two-level communication system to tackle challenges such as partial observability and inter-agent cooperation. Communication is separately utilised within the learned world models and within the learned policies of each agent to enhance modelling and task-solvin"},"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":"2406.13600","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-19T14:42:40Z","cross_cats_sorted":[],"title_canon_sha256":"daef7557dd2bf6c6212a20a61c12fe37130df24278e69c292d22dad775f336be","abstract_canon_sha256":"57f095f706032659b1674930bd70d5051365939ab9c6435522dc5d4650c0c52e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:32.366963Z","signature_b64":"erbx+NUEeGVd7XEKt6e00pc6lk2J0v6HxoA16KLdm3FHsqpk7rVGz1Cic/CGH14Gvx1gsZHyR9DXg4DPjIa3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35219d7382cdfaef9692144791ea36bf3d1d7ef1262344d0e9f958d4c79beee0","last_reissued_at":"2026-07-05T08:34:32.366522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:32.366522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoDreamer: Communication-Based Decentralised World Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amanda Prorok, Edan Toledo","submitted_at":"2024-06-19T14:42:40Z","abstract_excerpt":"Sample efficiency is a critical challenge in reinforcement learning. Model-based RL has emerged as a solution, but its application has largely been confined to single-agent scenarios. In this work, we introduce CoDreamer, an extension of the Dreamer algorithm for multi-agent environments. CoDreamer leverages Graph Neural Networks for a two-level communication system to tackle challenges such as partial observability and inter-agent cooperation. Communication is separately utilised within the learned world models and within the learned policies of each agent to enhance modelling and task-solvin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13600","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/2406.13600/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":"2406.13600","created_at":"2026-07-05T08:34:32.366578+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13600v1","created_at":"2026-07-05T08:34:32.366578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13600","created_at":"2026-07-05T08:34:32.366578+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUQZ244CZX5O","created_at":"2026-07-05T08:34:32.366578+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUQZ244CZX5O7FUS","created_at":"2026-07-05T08:34:32.366578+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUQZ244C","created_at":"2026-07-05T08:34:32.366578+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":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GUQZ244CZX5O7FUSCRDZD2RWX4","json":"https://pith.science/pith/GUQZ244CZX5O7FUSCRDZD2RWX4.json","graph_json":"https://pith.science/api/pith-number/GUQZ244CZX5O7FUSCRDZD2RWX4/graph.json","events_json":"https://pith.science/api/pith-number/GUQZ244CZX5O7FUSCRDZD2RWX4/events.json","paper":"https://pith.science/paper/GUQZ244C"},"agent_actions":{"view_html":"https://pith.science/pith/GUQZ244CZX5O7FUSCRDZD2RWX4","download_json":"https://pith.science/pith/GUQZ244CZX5O7FUSCRDZD2RWX4.json","view_paper":"https://pith.science/paper/GUQZ244C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13600&json=true","fetch_graph":"https://pith.science/api/pith-number/GUQZ244CZX5O7FUSCRDZD2RWX4/graph.json","fetch_events":"https://pith.science/api/pith-number/GUQZ244CZX5O7FUSCRDZD2RWX4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUQZ244CZX5O7FUSCRDZD2RWX4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUQZ244CZX5O7FUSCRDZD2RWX4/action/storage_attestation","attest_author":"https://pith.science/pith/GUQZ244CZX5O7FUSCRDZD2RWX4/action/author_attestation","sign_citation":"https://pith.science/pith/GUQZ244CZX5O7FUSCRDZD2RWX4/action/citation_signature","submit_replication":"https://pith.science/pith/GUQZ244CZX5O7FUSCRDZD2RWX4/action/replication_record"}},"created_at":"2026-07-05T08:34:32.366578+00:00","updated_at":"2026-07-05T08:34:32.366578+00:00"}