{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T3QDGSFLV63G2LOQXBWKAWCFGD","short_pith_number":"pith:T3QDGSFL","schema_version":"1.0","canonical_sha256":"9ee03348abafb66d2dd0b86ca0584530eb20a6e883b750d87982391b1f4ffbd6","source":{"kind":"arxiv","id":"2411.19639","version":1},"attestation_state":"computed","paper":{"title":"RMIO: A Model-Based MARL Framework for Scenarios with Observation Loss in Some Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Meiqin Liu, Ronghao Zheng, Senlin Zhang, Shanling Dong, Zifeng Shi","submitted_at":"2024-11-29T11:45:21Z","abstract_excerpt":"In recent years, model-based reinforcement learning (MBRL) has emerged as a solution to address sample complexity in multi-agent reinforcement learning (MARL) by modeling agent-environment dynamics to improve sample efficiency. However, most MBRL methods assume complete and continuous observations from each agent during the inference stage, which can be overly idealistic in practical applications. A novel model-based MARL approach called RMIO is introduced to address this limitation, specifically designed for scenarios where observation is lost in some agent. RMIO leverages the world model to "},"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":"2411.19639","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2024-11-29T11:45:21Z","cross_cats_sorted":[],"title_canon_sha256":"7fd9d6b906426c39bbb21f7344a74f293d0fc2e92011082f78c6b1f188b4ebb4","abstract_canon_sha256":"3c51e6aa4591517ffb3a871d244ac5a74be6cbec7a7b5d0def7be1a6adeb56da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:01:58.263962Z","signature_b64":"jGXHPI71Q68zeaK+PSJdwE5twc1lrDzx0b10ADqwVMy9I3R97xT4h15WZXkXNrCojR6jTTwnw2+7DY4XAUetBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ee03348abafb66d2dd0b86ca0584530eb20a6e883b750d87982391b1f4ffbd6","last_reissued_at":"2026-07-05T10:01:58.263482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:01:58.263482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RMIO: A Model-Based MARL Framework for Scenarios with Observation Loss in Some Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Meiqin Liu, Ronghao Zheng, Senlin Zhang, Shanling Dong, Zifeng Shi","submitted_at":"2024-11-29T11:45:21Z","abstract_excerpt":"In recent years, model-based reinforcement learning (MBRL) has emerged as a solution to address sample complexity in multi-agent reinforcement learning (MARL) by modeling agent-environment dynamics to improve sample efficiency. However, most MBRL methods assume complete and continuous observations from each agent during the inference stage, which can be overly idealistic in practical applications. A novel model-based MARL approach called RMIO is introduced to address this limitation, specifically designed for scenarios where observation is lost in some agent. RMIO leverages the world model to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.19639","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/2411.19639/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":"2411.19639","created_at":"2026-07-05T10:01:58.263546+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.19639v1","created_at":"2026-07-05T10:01:58.263546+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.19639","created_at":"2026-07-05T10:01:58.263546+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3QDGSFLV63G","created_at":"2026-07-05T10:01:58.263546+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3QDGSFLV63G2LOQ","created_at":"2026-07-05T10:01:58.263546+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3QDGSFL","created_at":"2026-07-05T10:01:58.263546+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05812","citing_title":"Multi-Agent Reinforcement Learning in Wireless Distributed Networks for 6G","ref_index":206,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD","json":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD.json","graph_json":"https://pith.science/api/pith-number/T3QDGSFLV63G2LOQXBWKAWCFGD/graph.json","events_json":"https://pith.science/api/pith-number/T3QDGSFLV63G2LOQXBWKAWCFGD/events.json","paper":"https://pith.science/paper/T3QDGSFL"},"agent_actions":{"view_html":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD","download_json":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD.json","view_paper":"https://pith.science/paper/T3QDGSFL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.19639&json=true","fetch_graph":"https://pith.science/api/pith-number/T3QDGSFLV63G2LOQXBWKAWCFGD/graph.json","fetch_events":"https://pith.science/api/pith-number/T3QDGSFLV63G2LOQXBWKAWCFGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/action/storage_attestation","attest_author":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/action/author_attestation","sign_citation":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/action/citation_signature","submit_replication":"https://pith.science/pith/T3QDGSFLV63G2LOQXBWKAWCFGD/action/replication_record"}},"created_at":"2026-07-05T10:01:58.263546+00:00","updated_at":"2026-07-05T10:01:58.263546+00:00"}