{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/comparative-evaluation-of-multi-agent-deep","title":"Benchmarking Multi-Agent Deep Reinforcement Learning Algorithms in Cooperative Tasks","arxiv_id":"2006.07869","date":"2020-06-14","proceeding":null,"authors":["Georgios Papoudakis","Filippos Christianos","Lukas Schäfer","Stefano V. Albrecht"],"abstract":"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 learning approaches. We open-source EPyMARL, which extends the PyMARL codebase to include additional algorithms and allow for flexible configuration of algorithm implementation details such as parameter sharing. Finally, we open-source two environments for multi-agent research which focus on coordination under sparse rewards.","url_abs":"https://arxiv.org/abs/2006.07869v4","url_pdf":"https://arxiv.org/pdf/2006.07869v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"comparative-evaluation-of-multi-agent-deep","repo_url":"https://github.com/uoe-agents/epymarl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"comparative-evaluation-of-multi-agent-deep","repo_url":"https://github.com/uoe-agents/robotic-warehouse","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"comparative-evaluation-of-multi-agent-deep","repo_url":"https://github.com/uoe-agents/lb-foraging","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"comparative-evaluation-of-multi-agent-deep","repo_url":"https://github.com/ShashwatNigam99/MARBLER","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"comparative-evaluation-of-multi-agent-deep","repo_url":"https://github.com/ailabdsunipi/pymarlzooplus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"comparative-evaluation-of-multi-agent-deep","repo_url":"https://github.com/dtabas/epymarl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"comparative-evaluation-of-multi-agent-deep","repo_url":"https://github.com/kinalmehta/epymarl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"comparative-evaluation-of-multi-agent-deep","repo_url":"https://github.com/semitable/robotic-warehouse","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"comparative-evaluation-of-multi-agent-deep","repo_url":"https://github.com/uoe-agents/revisiting-maddpg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.07869","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.07869"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/uoe-agents/lb-foraging","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/uoe-agents/epymarl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uoe-agents/robotic-warehouse","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dtabas/epymarl","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/semitable/robotic-warehouse","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kinalmehta/epymarl","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uoe-agents/revisiting-maddpg","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ailabdsunipi/pymarlzooplus","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ShashwatNigam99/MARBLER","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran":3,"ran_honours":1,"unverified":5},"by_repo_kind":{"listed":{"samples":9,"ran":4,"repositories":3}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":7,"samples":[{"code_sha256_prefix":"fa9a1eda0ac523d2","entry":"extract_alg_name_from_config","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fa9a1eda0ac523d2"}},{"code_sha256_prefix":"cf0832c848510d11","entry":"extract_env_name_from_config","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"cf0832c848510d11"}},{"code_sha256_prefix":"355d7b51c7ffd042","entry":"gumbel_softmax_sample","repo":"dtabas/epymarl","repo_kind":"listed","path":"src/controllers/maddpg_controller.py","file_url":"https://github.com/dtabas/epymarl/blob/HEAD/src/controllers/maddpg_controller.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"355d7b51c7ffd042"}},{"code_sha256_prefix":"73de3ace29add240","entry":"load_results","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"73de3ace29add240"}},{"code_sha256_prefix":"046b92243aae4f76","entry":"onehot_from_logits","repo":"dtabas/epymarl","repo_kind":"listed","path":"src/controllers/maddpg_controller.py","file_url":"https://github.com/dtabas/epymarl/blob/HEAD/src/controllers/maddpg_controller.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"046b92243aae4f76"}},{"code_sha256_prefix":"3695d66ab681cacf","entry":"sample_gumbel","repo":"dtabas/epymarl","repo_kind":"listed","path":"src/controllers/maddpg_controller.py","file_url":"https://github.com/dtabas/epymarl/blob/HEAD/src/controllers/maddpg_controller.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"3695d66ab681cacf"}},{"code_sha256_prefix":"930812c3b06fc858","entry":"work","repo":"dtabas/epymarl","repo_kind":"listed","path":"src/search.py","file_url":"https://github.com/dtabas/epymarl/blob/HEAD/src/search.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":false,"mcp_get_code":{"code_sha256":"930812c3b06fc858"}},{"code_sha256_prefix":"176e514fbf32fef9","entry":"convert_to_robotarium_poses","repo":"ShashwatNigam99/MARBLER","repo_kind":"listed","path":"robotarium_gym/utilities/misc.py","file_url":"https://github.com/ShashwatNigam99/MARBLER/blob/HEAD/robotarium_gym/utilities/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"176e514fbf32fef9"}},{"code_sha256_prefix":"d681f8b5572da32a","entry":"get_display","repo":"semitable/robotic-warehouse","repo_kind":"listed","path":"rware/rendering.py","file_url":"https://github.com/semitable/robotic-warehouse/blob/HEAD/rware/rendering.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d681f8b5572da32a"}},{"code_sha256_prefix":"e766f65debc9e598","entry":"get_max_reward","repo":"ShashwatNigam99/MARBLER","repo_kind":"listed","path":"epymarl-logparse.py","file_url":"https://github.com/ShashwatNigam99/MARBLER/blob/HEAD/epymarl-logparse.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e766f65debc9e598"}},{"code_sha256_prefix":"7fbfb1102413922b","entry":"get_nearest_neighbors","repo":"ShashwatNigam99/MARBLER","repo_kind":"listed","path":"robotarium_gym/utilities/misc.py","file_url":"https://github.com/ShashwatNigam99/MARBLER/blob/HEAD/robotarium_gym/utilities/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7fbfb1102413922b"}},{"code_sha256_prefix":"a4f3813a0404f041","entry":"is_close","repo":"ShashwatNigam99/MARBLER","repo_kind":"listed","path":"robotarium_gym/utilities/misc.py","file_url":"https://github.com/ShashwatNigam99/MARBLER/blob/HEAD/robotarium_gym/utilities/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a4f3813a0404f041"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}