{"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/a-policy-gradient-algorithm-for-learning-to-1","title":"A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning","arxiv_id":"2011.00382","date":"2020-10-31","proceeding":null,"authors":["Dong-Ki Kim","Miao Liu","Matthew Riemer","Chuangchuang Sun","Marwa Abdulhai","Golnaz Habibi","Sebastian Lopez-Cot","Gerald Tesauro","Jonathan P. How"],"abstract":"A fundamental challenge in multiagent reinforcement learning is to learn beneficial behaviors in a shared environment with other simultaneously learning agents. In particular, each agent perceives the environment as effectively non-stationary due to the changing policies of other agents. Moreover, each agent is itself constantly learning, leading to natural non-stationarity in the distribution of experiences encountered. In this paper, we propose a novel meta-multiagent policy gradient theorem that directly accounts for the non-stationary policy dynamics inherent to multiagent learning settings. This is achieved by modeling our gradient updates to consider both an agent's own non-stationary policy dynamics and the non-stationary policy dynamics of other agents in the environment. We show that our theoretically grounded approach provides a general solution to the multiagent learning problem, which inherently comprises all key aspects of previous state of the art approaches on this topic. We test our method on a diverse suite of multiagent benchmarks and demonstrate a more efficient ability to adapt to new agents as they learn than baseline methods across the full spectrum of mixed incentive, competitive, and cooperative domains.","url_abs":"https://arxiv.org/abs/2011.00382v5","url_pdf":"https://arxiv.org/pdf/2011.00382v5.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":"a-policy-gradient-algorithm-for-learning-to-1","repo_url":"https://github.com/dkkim93/meta-mapg","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":{"syntology_url":"https://syntology.ai/paper/2011.00382","atlas_url":"https://app.syntology.ai/?focus=2011.00382","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.00382"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/alexis-jacq/LOLA","reach":null},{"provenance":"deterministic:regex_extraction","url":"https://github.com/schroederdewitt/multiagent","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dkkim93/meta-mapg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_honours":2,"unverified":5},"by_repo_kind":{"official":{"samples":4,"ran":0,"repositories":1},"found_in_text":{"samples":4,"ran":3,"repositories":1}},"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":0,"samples":[{"code_sha256_prefix":"d43d42fecfa6b959","entry":"build_grads","repo":"alexis-jacq/LOLA","repo_kind":"found_in_text","path":"lola_dice/rpg.py","file_url":"https://github.com/alexis-jacq/LOLA/blob/HEAD/lola_dice/rpg.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d43d42fecfa6b959"}},{"code_sha256_prefix":"83c18353fc1e61a1","entry":"build_losses","repo":"alexis-jacq/LOLA","repo_kind":"found_in_text","path":"lola_dice/rpg.py","file_url":"https://github.com/alexis-jacq/LOLA/blob/HEAD/lola_dice/rpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83c18353fc1e61a1"}},{"code_sha256_prefix":"cfc6f16a78f519bd","entry":"stop_forward","repo":"alexis-jacq/LOLA","repo_kind":"found_in_text","path":"lola_dice/rpg.py","file_url":"https://github.com/alexis-jacq/LOLA/blob/HEAD/lola_dice/rpg.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cfc6f16a78f519bd"}},{"code_sha256_prefix":"3084c14c98bf7e53","entry":"build_new_params","repo":"alexis-jacq/LOLA","repo_kind":"found_in_text","path":"lola_dice/rpg.py","file_url":"https://github.com/alexis-jacq/LOLA/blob/HEAD/lola_dice/rpg.py","link_basis":"first_harvest_node","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":"3084c14c98bf7e53"}},{"code_sha256_prefix":"2a6aa3337b478e39","entry":"get_dice_loss","repo":"dkkim93/meta-mapg","repo_kind":"official","path":"meta/dice.py","file_url":"https://github.com/dkkim93/meta-mapg/blob/HEAD/meta/dice.py","link_basis":"first_harvest_node","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":"2a6aa3337b478e39"}},{"code_sha256_prefix":"f006932feacd0d06","entry":"lstm_cell","repo":"dkkim93/meta-mapg","repo_kind":"official","path":"network/categorical_lstm.py","file_url":"https://github.com/dkkim93/meta-mapg/blob/HEAD/network/categorical_lstm.py","link_basis":"first_harvest_node","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":"f006932feacd0d06"}},{"code_sha256_prefix":"17699ef2e449301d","entry":"magic_box","repo":"dkkim93/meta-mapg","repo_kind":"official","path":"meta/dice.py","file_url":"https://github.com/dkkim93/meta-mapg/blob/HEAD/meta/dice.py","link_basis":"first_harvest_node","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":"17699ef2e449301d"}},{"code_sha256_prefix":"fdc3c01715c2c370","entry":"pc_grad","repo":"dkkim93/meta-mapg","repo_kind":"official","path":"meta/projection_grad.py","file_url":"https://github.com/dkkim93/meta-mapg/blob/HEAD/meta/projection_grad.py","link_basis":"first_harvest_node","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":"fdc3c01715c2c370"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}