{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:P7TTZ2I5LE5ZPUXXEOD7MFRMUK","short_pith_number":"pith:P7TTZ2I5","schema_version":"1.0","canonical_sha256":"7fe73ce91d593b97d2f72387f6162ca29e9622967e13e8cce641ed0a802e246d","source":{"kind":"arxiv","id":"2011.09533","version":1},"attestation_state":"computed","paper":{"title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christian Schroeder de Witt, Denys Makoviichuk, Mingfei Sun, Philip H.S. Torr, Shimon Whiteson, Tarun Gupta, Viktor Makoviychuk","submitted_at":"2020-11-18T20:29:59Z","abstract_excerpt":"Most recently developed approaches to cooperative multi-agent reinforcement learning in the \\emph{centralized training with decentralized execution} setting involve estimating a centralized, joint value function. In this paper, we demonstrate that, despite its various theoretical shortcomings, Independent PPO (IPPO), a form of independent learning in which each agent simply estimates its local value function, can perform just as well as or better than state-of-the-art joint learning approaches on popular multi-agent benchmark suite SMAC with little hyperparameter tuning. We also compare IPPO t"},"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":"2011.09533","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2020-11-18T20:29:59Z","cross_cats_sorted":[],"title_canon_sha256":"d0934ca310fa621fc27aed96a6927d942be131554aec5259e08c02e0d6e190d1","abstract_canon_sha256":"914b87d017d3bd758a4b1ea031ab23833d75e94682a2d0294a79502e8e770737"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:52:49.495932Z","signature_b64":"OBIfhR11mvHndF1JCFK4e54ztJGD8g9dPeEp7trfvVa7e6AkAH088gzEYvO1rouMCom4CtrWlzKPpRpEfambBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7fe73ce91d593b97d2f72387f6162ca29e9622967e13e8cce641ed0a802e246d","last_reissued_at":"2026-07-05T01:52:49.495442Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:52:49.495442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Independent Learning All You Need in the StarCraft Multi-Agent Challenge?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Christian Schroeder de Witt, Denys Makoviichuk, Mingfei Sun, Philip H.S. Torr, Shimon Whiteson, Tarun Gupta, Viktor Makoviychuk","submitted_at":"2020-11-18T20:29:59Z","abstract_excerpt":"Most recently developed approaches to cooperative multi-agent reinforcement learning in the \\emph{centralized training with decentralized execution} setting involve estimating a centralized, joint value function. In this paper, we demonstrate that, despite its various theoretical shortcomings, Independent PPO (IPPO), a form of independent learning in which each agent simply estimates its local value function, can perform just as well as or better than state-of-the-art joint learning approaches on popular multi-agent benchmark suite SMAC with little hyperparameter tuning. We also compare IPPO t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.09533","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/2011.09533/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":"2011.09533","created_at":"2026-07-05T01:52:49.495502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.09533v1","created_at":"2026-07-05T01:52:49.495502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.09533","created_at":"2026-07-05T01:52:49.495502+00:00"},{"alias_kind":"pith_short_12","alias_value":"P7TTZ2I5LE5Z","created_at":"2026-07-05T01:52:49.495502+00:00"},{"alias_kind":"pith_short_16","alias_value":"P7TTZ2I5LE5ZPUXX","created_at":"2026-07-05T01:52:49.495502+00:00"},{"alias_kind":"pith_short_8","alias_value":"P7TTZ2I5","created_at":"2026-07-05T01:52:49.495502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25526","citing_title":"Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09958","citing_title":"Uncertainty-Aware Motion Planning for Autonomous Driving in Mixed Traffic Environment","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08340","citing_title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29126","citing_title":"HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00324","citing_title":"Queue-Aware Graph Reinforcement Learning for UAV-ISAC-Assisted Maritime Data Collection","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":136,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20255","citing_title":"Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29126","citing_title":"HiComm: Hierarchical Communication for Multi-agent Reinforcement Learning","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13076","citing_title":"$\\alpha$-fair heterogeneous agent reinforcement learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2602.01665","citing_title":"TABX: A High-Throughput Sandbox Battle Simulator for Multi-Agent Reinforcement Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23652","citing_title":"One Policy, Infinite NPCs: Persona-Traceable Shared RL Policies for Scalable Game Agents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23562","citing_title":"ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20255","citing_title":"Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08391","citing_title":"SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19235","citing_title":"GAE Falls Short in Imperfect-Information Self-Play Reinforcement Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2507.15351","citing_title":"One Step is Enough: Multi-Agent Reinforcement Learning based on One-Step Policy Optimization for Order Dispatch on Ride-Sharing Platforms","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2508.01049","citing_title":"Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.17676","citing_title":"GLo-MAPPO: Multi-Agent Deep Reinforcement Learning for Energy-Efficient UAV-Assisted LoRa Networks","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21972","citing_title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11688","citing_title":"Shaping Zero-Shot Coordination via State Blocking","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10482","citing_title":"Priority-Driven Control and Communication in Decentralized Multi-Agent Systems via Reinforcement Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08391","citing_title":"SACHI: Structured Agent Coordination via Holistic Information Integration in Multi-Agent Reinforcement Learning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09212","citing_title":"Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10482","citing_title":"Priority-Driven Control and Communication in Decentralized Multi-Agent Systems via Reinforcement Learning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04741","citing_title":"Hierarchical Multiagent Reinforcement Learning for Multi-Group Tax Game","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P7TTZ2I5LE5ZPUXXEOD7MFRMUK","json":"https://pith.science/pith/P7TTZ2I5LE5ZPUXXEOD7MFRMUK.json","graph_json":"https://pith.science/api/pith-number/P7TTZ2I5LE5ZPUXXEOD7MFRMUK/graph.json","events_json":"https://pith.science/api/pith-number/P7TTZ2I5LE5ZPUXXEOD7MFRMUK/events.json","paper":"https://pith.science/paper/P7TTZ2I5"},"agent_actions":{"view_html":"https://pith.science/pith/P7TTZ2I5LE5ZPUXXEOD7MFRMUK","download_json":"https://pith.science/pith/P7TTZ2I5LE5ZPUXXEOD7MFRMUK.json","view_paper":"https://pith.science/paper/P7TTZ2I5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.09533&json=true","fetch_graph":"https://pith.science/api/pith-number/P7TTZ2I5LE5ZPUXXEOD7MFRMUK/graph.json","fetch_events":"https://pith.science/api/pith-number/P7TTZ2I5LE5ZPUXXEOD7MFRMUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P7TTZ2I5LE5ZPUXXEOD7MFRMUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P7TTZ2I5LE5ZPUXXEOD7MFRMUK/action/storage_attestation","attest_author":"https://pith.science/pith/P7TTZ2I5LE5ZPUXXEOD7MFRMUK/action/author_attestation","sign_citation":"https://pith.science/pith/P7TTZ2I5LE5ZPUXXEOD7MFRMUK/action/citation_signature","submit_replication":"https://pith.science/pith/P7TTZ2I5LE5ZPUXXEOD7MFRMUK/action/replication_record"}},"created_at":"2026-07-05T01:52:49.495502+00:00","updated_at":"2026-07-05T01:52:49.495502+00:00"}