{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:ABIRKBBTAWTPQ7FX5DGR3BUQGN","short_pith_number":"pith:ABIRKBBT","schema_version":"1.0","canonical_sha256":"005115043305a6f87cb7e8cd1d8690336190331ae54ab49b7b2d2f42593e6fad","source":{"kind":"arxiv","id":"2006.07869","version":4},"attestation_state":"computed","paper":{"title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Filippos Christianos, Georgios Papoudakis, Lukas Sch\\\"afer, Stefano V. Albrecht","submitted_at":"2020-06-14T11:22:53Z","abstract_excerpt":"Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three different classes of MARL algorithms (independent learning, centralised multi-agent policy gradient, value decomposition) in a diverse range of cooperative multi-agent learning tasks. Our experiments serve as a reference for the expected performance of algorithms across different learning tasks, and we provide insights regarding the effectiveness of different l"},"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":"2006.07869","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-14T11:22:53Z","cross_cats_sorted":["cs.AI","cs.MA","stat.ML"],"title_canon_sha256":"4c9a295385164feb1fe58a166c889e21480ddd1838c89722acaeddae9a6c7ce0","abstract_canon_sha256":"368685add8c733e2e28be8e4c1d0015cc9ac2e8efcc71c02bf026edb27328379"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:30:06.318287Z","signature_b64":"UzZlru+Ny218ovk3EfxrObHPKG6RW6vY+eEQ58nR5cLAc7n0oUdHcYSpt8NZT4b6GeZX8T4aJkWwuw75nQCqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"005115043305a6f87cb7e8cd1d8690336190331ae54ab49b7b2d2f42593e6fad","last_reissued_at":"2026-07-05T03:30:06.317277Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:30:06.317277Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA","stat.ML"],"primary_cat":"cs.LG","authors_text":"Filippos Christianos, Georgios Papoudakis, Lukas Sch\\\"afer, Stefano V. Albrecht","submitted_at":"2020-06-14T11:22:53Z","abstract_excerpt":"Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three different classes of MARL algorithms (independent learning, centralised multi-agent policy gradient, value decomposition) in a diverse range of cooperative multi-agent learning tasks. Our experiments serve as a reference for the expected performance of algorithms across different learning tasks, and we provide insights regarding the effectiveness of different l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07869","kind":"arxiv","version":4},"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/2006.07869/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":"2006.07869","created_at":"2026-07-05T03:30:06.317360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.07869v4","created_at":"2026-07-05T03:30:06.317360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07869","created_at":"2026-07-05T03:30:06.317360+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABIRKBBTAWTP","created_at":"2026-07-05T03:30:06.317360+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABIRKBBTAWTPQ7FX","created_at":"2026-07-05T03:30:06.317360+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABIRKBBT","created_at":"2026-07-05T03:30:06.317360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"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":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12655","citing_title":"Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18024","citing_title":"Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25867","citing_title":"CINOC: Cardinality-Invariant Neural Operator Policies for Scalable PDE Control","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2502.03506","citing_title":"Optimistic {\\epsilon}-Greedy Exploration for Cooperative Multi-Agent Reinforcement Learning","ref_index":16,"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":51,"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":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.14135","citing_title":"AdaFair-MARL: Enforcing Adaptive Fairness Constraints in Multi-Agent Reinforcement Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23964","citing_title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12555","citing_title":"DelAC: A Multi-agent Reinforcement Learning of Team-Symmetric Stochastic Games","ref_index":28,"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":51,"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":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03842","citing_title":"SOAR: Real-Time Joint Optimization of Order Allocation and Robot Scheduling in Robotic Mobile Fulfillment Systems","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18190","citing_title":"Scalable Neighborhood-Based Multi-Agent Actor-Critic","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABIRKBBTAWTPQ7FX5DGR3BUQGN","json":"https://pith.science/pith/ABIRKBBTAWTPQ7FX5DGR3BUQGN.json","graph_json":"https://pith.science/api/pith-number/ABIRKBBTAWTPQ7FX5DGR3BUQGN/graph.json","events_json":"https://pith.science/api/pith-number/ABIRKBBTAWTPQ7FX5DGR3BUQGN/events.json","paper":"https://pith.science/paper/ABIRKBBT"},"agent_actions":{"view_html":"https://pith.science/pith/ABIRKBBTAWTPQ7FX5DGR3BUQGN","download_json":"https://pith.science/pith/ABIRKBBTAWTPQ7FX5DGR3BUQGN.json","view_paper":"https://pith.science/paper/ABIRKBBT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.07869&json=true","fetch_graph":"https://pith.science/api/pith-number/ABIRKBBTAWTPQ7FX5DGR3BUQGN/graph.json","fetch_events":"https://pith.science/api/pith-number/ABIRKBBTAWTPQ7FX5DGR3BUQGN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABIRKBBTAWTPQ7FX5DGR3BUQGN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABIRKBBTAWTPQ7FX5DGR3BUQGN/action/storage_attestation","attest_author":"https://pith.science/pith/ABIRKBBTAWTPQ7FX5DGR3BUQGN/action/author_attestation","sign_citation":"https://pith.science/pith/ABIRKBBTAWTPQ7FX5DGR3BUQGN/action/citation_signature","submit_replication":"https://pith.science/pith/ABIRKBBTAWTPQ7FX5DGR3BUQGN/action/replication_record"}},"created_at":"2026-07-05T03:30:06.317360+00:00","updated_at":"2026-07-05T03:30:06.317360+00:00"}