{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UY6UEHKBKF6YCZ5NW6APFQKMK3","short_pith_number":"pith:UY6UEHKB","schema_version":"1.0","canonical_sha256":"a63d421d41517d8167adb780f2c14c56f4f55285396fc2a61aa0134b277eba3a","source":{"kind":"arxiv","id":"2301.01649","version":6},"attestation_state":"computed","paper":{"title":"Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Claudia Linnhoff-Popien, Fabian Ritz, Jonas N\\\"u{\\ss}lein, Maximilian Zorn, Michael K\\\"olle, Philipp Altmann, Thomas Gabor, Thomy Phan","submitted_at":"2023-01-04T14:48:25Z","abstract_excerpt":"Stochastic partial observability poses a major challenge for decentralized coordination in multi-agent reinforcement learning but is largely neglected in state-of-the-art research due to a strong focus on state-based centralized training for decentralized execution (CTDE) and benchmarks that lack sufficient stochasticity like StarCraft Multi-Agent Challenge (SMAC). In this paper, we propose Attention-based Embeddings of Recurrence In multi-Agent Learning (AERIAL) to approximate value functions under stochastic partial observability. AERIAL replaces the true state with a learned representation "},"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":"2301.01649","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MA","submitted_at":"2023-01-04T14:48:25Z","cross_cats_sorted":[],"title_canon_sha256":"54c320eaf1e793d97e02acb1a3b6a75e5810004e0c18086181ec4521653a4b3c","abstract_canon_sha256":"bf20a6d3594120427f067180e2320c3a3c14e891718c1d7fb35f83f8ec4a9a91"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:28:26.869353Z","signature_b64":"LTgPwksn/N5shTArvpoxeKmDrLYCFB/6be7+Z0nQbNCo1bFfNdmiSl+SDThDPkJSHSYJuncVlZOQjiP6LVsxAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a63d421d41517d8167adb780f2c14c56f4f55285396fc2a61aa0134b277eba3a","last_reissued_at":"2026-07-05T07:28:26.868859Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:28:26.868859Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MA","authors_text":"Claudia Linnhoff-Popien, Fabian Ritz, Jonas N\\\"u{\\ss}lein, Maximilian Zorn, Michael K\\\"olle, Philipp Altmann, Thomas Gabor, Thomy Phan","submitted_at":"2023-01-04T14:48:25Z","abstract_excerpt":"Stochastic partial observability poses a major challenge for decentralized coordination in multi-agent reinforcement learning but is largely neglected in state-of-the-art research due to a strong focus on state-based centralized training for decentralized execution (CTDE) and benchmarks that lack sufficient stochasticity like StarCraft Multi-Agent Challenge (SMAC). In this paper, we propose Attention-based Embeddings of Recurrence In multi-Agent Learning (AERIAL) to approximate value functions under stochastic partial observability. AERIAL replaces the true state with a learned representation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.01649","kind":"arxiv","version":6},"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/2301.01649/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":"2301.01649","created_at":"2026-07-05T07:28:26.868916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.01649v6","created_at":"2026-07-05T07:28:26.868916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.01649","created_at":"2026-07-05T07:28:26.868916+00:00"},{"alias_kind":"pith_short_12","alias_value":"UY6UEHKBKF6Y","created_at":"2026-07-05T07:28:26.868916+00:00"},{"alias_kind":"pith_short_16","alias_value":"UY6UEHKBKF6YCZ5N","created_at":"2026-07-05T07:28:26.868916+00:00"},{"alias_kind":"pith_short_8","alias_value":"UY6UEHKB","created_at":"2026-07-05T07:28:26.868916+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UY6UEHKBKF6YCZ5NW6APFQKMK3","json":"https://pith.science/pith/UY6UEHKBKF6YCZ5NW6APFQKMK3.json","graph_json":"https://pith.science/api/pith-number/UY6UEHKBKF6YCZ5NW6APFQKMK3/graph.json","events_json":"https://pith.science/api/pith-number/UY6UEHKBKF6YCZ5NW6APFQKMK3/events.json","paper":"https://pith.science/paper/UY6UEHKB"},"agent_actions":{"view_html":"https://pith.science/pith/UY6UEHKBKF6YCZ5NW6APFQKMK3","download_json":"https://pith.science/pith/UY6UEHKBKF6YCZ5NW6APFQKMK3.json","view_paper":"https://pith.science/paper/UY6UEHKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.01649&json=true","fetch_graph":"https://pith.science/api/pith-number/UY6UEHKBKF6YCZ5NW6APFQKMK3/graph.json","fetch_events":"https://pith.science/api/pith-number/UY6UEHKBKF6YCZ5NW6APFQKMK3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UY6UEHKBKF6YCZ5NW6APFQKMK3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UY6UEHKBKF6YCZ5NW6APFQKMK3/action/storage_attestation","attest_author":"https://pith.science/pith/UY6UEHKBKF6YCZ5NW6APFQKMK3/action/author_attestation","sign_citation":"https://pith.science/pith/UY6UEHKBKF6YCZ5NW6APFQKMK3/action/citation_signature","submit_replication":"https://pith.science/pith/UY6UEHKBKF6YCZ5NW6APFQKMK3/action/replication_record"}},"created_at":"2026-07-05T07:28:26.868916+00:00","updated_at":"2026-07-05T07:28:26.868916+00:00"}