{"id":13471756,"url":"https://github.com/EzgiKorkmaz/adversarial-reinforcement-learning","last_synced_at":"2025-03-26T14:32:26.840Z","repository":{"id":193592254,"uuid":"689102862","full_name":"EzgiKorkmaz/adversarial-reinforcement-learning","owner":"EzgiKorkmaz","description":"Reading list for adversarial perspective and robustness in deep reinforcement learning.","archived":false,"fork":false,"pushed_at":"2024-06-18T15:10:05.000Z","size":17,"stargazers_count":92,"open_issues_count":1,"forks_count":5,"subscribers_count":5,"default_branch":"main","last_synced_at":"2024-10-30T04:09:42.461Z","etag":null,"topics":["adversarial-machine-learning","adversarial-policies","adversarial-reinforcement-learning","ai-alignment","ai-safety","artificial-intelligence-alignment","deep-reinforcement-learning","explainable-machine-learning","machine-learning-safety","meta-reinforcement-learning","multiagent-reinforcement-learning","reinforcement-learning-alignment","reinforcement-learning-safety","responsible-ai","robust-deep-reinforcement-learning","robust-machine-learning","robust-reinforcement-learning","safe-reinforcement-learning","safe-rlhf"],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/EzgiKorkmaz.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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":"2023-09-08T20:06:18.000Z","updated_at":"2024-10-23T00:12:51.000Z","dependencies_parsed_at":"2024-10-30T02:50:30.477Z","dependency_job_id":null,"html_url":"https://github.com/EzgiKorkmaz/adversarial-reinforcement-learning","commit_stats":{"total_commits":14,"total_committers":1,"mean_commits":14.0,"dds":0.0,"last_synced_commit":"b4fc15ff46144d2299d733817ed7bf73797e50bb"},"previous_names":["ezgikorkmaz/adversarial-reinforcement-learning"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EzgiKorkmaz%2Fadversarial-reinforcement-learning","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EzgiKorkmaz%2Fadversarial-reinforcement-learning/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EzgiKorkmaz%2Fadversarial-reinforcement-learning/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/EzgiKorkmaz%2Fadversarial-reinforcement-learning/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/EzgiKorkmaz","download_url":"https://codeload.github.com/EzgiKorkmaz/adversarial-reinforcement-learning/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245670991,"owners_count":20653465,"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","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":["adversarial-machine-learning","adversarial-policies","adversarial-reinforcement-learning","ai-alignment","ai-safety","artificial-intelligence-alignment","deep-reinforcement-learning","explainable-machine-learning","machine-learning-safety","meta-reinforcement-learning","multiagent-reinforcement-learning","reinforcement-learning-alignment","reinforcement-learning-safety","responsible-ai","robust-deep-reinforcement-learning","robust-machine-learning","robust-reinforcement-learning","safe-reinforcement-learning","safe-rlhf"],"created_at":"2024-07-31T16:00:49.040Z","updated_at":"2025-03-26T14:32:26.567Z","avatar_url":"https://github.com/EzgiKorkmaz.png","language":null,"funding_links":[],"categories":["Others"],"sub_categories":[],"readme":"# Adversarial Reinforcement Learning\n\n\n\nA curated reading list for the adversarial perspective in deep reinforcement learning. The list covers topics ranging from adversarial attacks on deep reinforcement learning policies to adversarial training techniques and interpretability in deep reinforcement learning robustness to adversarial state detection algortihms for robust decision making.\n\nDelving Into Adversarial Attacks on Deep Policies. ICLR Workshop 2017. [[Link]](https://arxiv.org/abs/1705.06452)\n\nAdversarial Attacks on Neural Network Policies. ICLR Workshop 2017. [[Link]](https://openreview.net/pdf?id=ryvlRyBKl)\n\nRobust Adversarial Reinforcement Learning. ICML 2017. [[Link]](http://proceedings.mlr.press/v70/pinto17a/pinto17a.pdf)\n\nAdversarial Policies: Attacking Deep Reinforcement Learning. ICLR 2020. [[Link]](https://openreview.net/pdf?id=HJgEMpVFwB)\n\nStealthy and Efficient Adversarial Attacks Against Deep Reinforcement Learning. AAAI 2020. [[Link]](https://ojs.aaai.org/index.php/AAAI/article/view/6047/5903)\n\nNesterov Momentum Adversarial Perturbations in the Deep Reinforcement Learning Domain. ICML Workshop 2020. [[Link]](https://biases-invariances-generalization.github.io/pdf/big_33.pdf)\n\nInvestigating Vulnerabilities of Deep Neural Policies. UAI 2021. [[Link]](https://proceedings.mlr.press/v161/korkmaz21a.html)\n\nDeep Reinforcement Learning Policies Learn Shared Adversarial Features Across MDPs. AAAI 2022. [[Link]](https://aaai.org/papers/07229-deep-reinforcement-learning-policies-learn-shared-adversarial-features-across-mdps/)\n\nAdversarial Robust Deep Reinforcement Learning Requires Redefining Robustness. AAAI 2023. [[Link]](https://ojs.aaai.org/index.php/AAAI/article/view/26009)\n\nDetecting Adversarial Directions in Deep Reinforcement Learning to Make Robust Decisions. ICML 2023. [[Link]](https://proceedings.mlr.press/v202/korkmaz23a.html)\n\nUnderstanding and Diagnosing Deep Reinforcement Learning. ICML 2024. [[Link]](https://openreview.net/pdf?id=s9RKqT7jVM)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEzgiKorkmaz%2Fadversarial-reinforcement-learning","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FEzgiKorkmaz%2Fadversarial-reinforcement-learning","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FEzgiKorkmaz%2Fadversarial-reinforcement-learning/lists"}