{"id":31211503,"url":"https://github.com/cyberagentailab/adaptively-perturbed-md","last_synced_at":"2025-09-21T05:28:43.256Z","repository":{"id":244357644,"uuid":"804705041","full_name":"CyberAgentAILab/adaptively-perturbed-md","owner":"CyberAgentAILab","description":null,"archived":false,"fork":false,"pushed_at":"2024-06-14T07:05:31.000Z","size":14,"stargazers_count":2,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-09-10T07:42:51.416Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CyberAgentAILab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-05-23T05:31:25.000Z","updated_at":"2024-10-07T14:50:58.000Z","dependencies_parsed_at":"2024-06-14T08:28:09.300Z","dependency_job_id":null,"html_url":"https://github.com/CyberAgentAILab/adaptively-perturbed-md","commit_stats":null,"previous_names":["cyberagentailab/adaptively-perturbed-md"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/CyberAgentAILab/adaptively-perturbed-md","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Fadaptively-perturbed-md","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Fadaptively-perturbed-md/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Fadaptively-perturbed-md/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Fadaptively-perturbed-md/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CyberAgentAILab","download_url":"https://codeload.github.com/CyberAgentAILab/adaptively-perturbed-md/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CyberAgentAILab%2Fadaptively-perturbed-md/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":276195623,"owners_count":25601151,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-21T02:00:07.055Z","response_time":72,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-09-21T05:28:42.110Z","updated_at":"2025-09-21T05:28:43.233Z","avatar_url":"https://github.com/CyberAgentAILab.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Adaptively Perturbed Mirror Descent for Learning in Games\n## tl;dr\nThis paper proposes a novel variant of Mirror Descent that achieves last-iterate convergence.\n\n## Installation\n```bash\npip install -r requirements.txt\n```\n\n## Run Experiments\nIn order to investigate the performance of APMD in Three-Player Biased Rock-Paper-Scissors with full feedback, execute the following command:\n```bash\n# D_{psi}=KL G=KL\n$ python main.py feedback=full n_trials=10 T=100000 game=three_biased_rps algorithm=APMD algorithm.learning_rate=0.1 algorithm.perturbation_strength=0.1 algorithm.random_init=True algorithm.regularizer=entropy algorithm.perturbation_divergence=kl algorithm.update_slingshot_freq=100\n# D_{psi}=KL G=Reverse KL\n$ python main.py feedback=full n_trials=10 T=100000 game=three_biased_rps algorithm=APMD algorithm.learning_rate=0.1 algorithm.perturbation_strength=0.1 algorithm.random_init=True algorithm.regularizer=entropy algorithm.perturbation_divergence=reverse_kl  algorithm.update_slingshot_freq=100\n# D_{psi}=Squared L2 G=Squared L2\n$ python main.py feedback=full n_trials=10 T=100000 game=three_biased_rps algorithm=APMD algorithm.learning_rate=0.1 algorithm.perturbation_strength=1.0 algorithm.random_init=True algorithm.regularizer=l2 algorithm.perturbation_divergence=l2 algorithm.update_slingshot_freq=20\n```\n\nTo evaluate APMD via an experiment in Three-Player Biased Rock-Paper-Scissors with noisy feedback, execute the following command:\n```bash\n# D_{psi}=KL G=KL\n$ python main.py feedback=noisy n_trials=10 T=100000 game=three_biased_rps algorithm=APMD algorithm.learning_rate=0.01 algorithm.perturbation_strength=0.1 algorithm.random_init=True algorithm.regularizer=entropy algorithm.perturbation_divergence=kl algorithm.update_slingshot_freq=1000\n# D_{psi}=KL G=Reverse KL\n$ python main.py feedback=noisy n_trials=10 T=100000 game=three_biased_rps algorithm=APMD algorithm.learning_rate=0.01 algorithm.perturbation_strength=0.1 algorithm.random_init=True algorithm.regularizer=entropy algorithm.perturbation_divergence=reverse_kl algorithm.update_slingshot_freq=1000\n# D_{psi}=Squared L2 G=Squared L2\n$ python main.py feedback=noisy n_trials=10 T=100000 game=three_biased_rps algorithm=APMD algorithm.learning_rate=0.01 algorithm.perturbation_strength=1.0 algorithm.random_init=True algorithm.regularizer=l2 algorithm.perturbation_divergence=l2 algorithm.update_slingshot_freq=200\n```\n\n## Reference\nKenshi Abe, Kaito Ariu, Mitsuki Sakamoto, and Atsushi Iwasaki. Adaptively perturbed mirror descent for learning in games. In ICML, 2024\n\n\nBibtex:\n```\n@inproceedings{\nabe2024adaptively,\n  title={Adaptively Perturbed Mirror Descent for Learning in Games},\n  author={Abe, Kenshi and Ariu, Kaito and Sakamoto, Mitsuki and Iwasaki, Atsushi},\n  booktitle={ICML},\n  year={2024}\n}\n```","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyberagentailab%2Fadaptively-perturbed-md","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcyberagentailab%2Fadaptively-perturbed-md","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcyberagentailab%2Fadaptively-perturbed-md/lists"}