{"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/deep-reinforcement-learning-for-imbalanced","title":"Deep Reinforcement Learning for Imbalanced Classification","arxiv_id":"1901.01379","date":"2019-01-05","proceeding":null,"authors":["Enlu Lin","Qiong Chen","Xiaoming Qi"],"abstract":"Data in real-world application often exhibit skewed class distribution which\nposes an intense challenge for machine learning. Conventional classification\nalgorithms are not effective in the case of imbalanced data distribution, and\nmay fail when the data distribution is highly imbalanced. To address this\nissue, we propose a general imbalanced classification model based on deep\nreinforcement learning. We formulate the classification problem as a sequential\ndecision-making process and solve it by deep Q-learning network. The agent\nperforms a classification action on one sample at each time step, and the\nenvironment evaluates the classification action and returns a reward to the\nagent. The reward from minority class sample is larger so the agent is more\nsensitive to the minority class. The agent finally finds an optimal\nclassification policy in imbalanced data under the guidance of specific reward\nfunction and beneficial learning environment. Experiments show that our\nproposed model outperforms the other imbalanced classification algorithms, and\nit can identify more minority samples and has great classification performance.","url_abs":"http://arxiv.org/abs/1901.01379v1","url_pdf":"http://arxiv.org/pdf/1901.01379v1.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":"deep-reinforcement-learning-for-imbalanced","repo_url":"https://github.com/linenus/DRL-For-imbalanced-Classification","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-reinforcement-learning-for-imbalanced","repo_url":"https://github.com/Denbergvanthijs/imbDRL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deep-reinforcement-learning-for-imbalanced","repo_url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"q-learning","task_name":"Q-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"},{"task_slug":"imbalanced-classification","task_name":"imbalanced classification"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dqn","method_name":"DQN"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"q-learning","method_name":"Q-Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.01379","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.01379"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Denbergvanthijs/imbDRL","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/linenus/DRL-For-imbalanced-Classification","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Montherapy/Deep-reinforcement-learning-for-multi-class-imbalanced-classification","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"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":"5aa844be0122f4ad","entry":"classification_metrics","repo":"Denbergvanthijs/imbDRL","repo_kind":"listed","path":"imbDRL/metrics.py","file_url":"https://github.com/Denbergvanthijs/imbDRL/blob/HEAD/imbDRL/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5aa844be0122f4ad"}},{"code_sha256_prefix":"9dfe3d986fc1480f","entry":"imbalance_ratio","repo":"Denbergvanthijs/imbDRL","repo_kind":"listed","path":"imbDRL/utils.py","file_url":"https://github.com/Denbergvanthijs/imbDRL/blob/HEAD/imbDRL/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9dfe3d986fc1480f"}},{"code_sha256_prefix":"692b71a43ff1f48c","entry":"load_csv","repo":"Denbergvanthijs/imbDRL","repo_kind":"listed","path":"imbDRL/data.py","file_url":"https://github.com/Denbergvanthijs/imbDRL/blob/HEAD/imbDRL/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"692b71a43ff1f48c"}},{"code_sha256_prefix":"cc6338a2307b8a02","entry":"load_image","repo":"Denbergvanthijs/imbDRL","repo_kind":"listed","path":"imbDRL/data.py","file_url":"https://github.com/Denbergvanthijs/imbDRL/blob/HEAD/imbDRL/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cc6338a2307b8a02"}},{"code_sha256_prefix":"5e662a534f1f56b2","entry":"load_imdb","repo":"Denbergvanthijs/imbDRL","repo_kind":"listed","path":"imbDRL/data.py","file_url":"https://github.com/Denbergvanthijs/imbDRL/blob/HEAD/imbDRL/data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e662a534f1f56b2"}},{"code_sha256_prefix":"318d9a939851a219","entry":"rounded_dict","repo":"Denbergvanthijs/imbDRL","repo_kind":"listed","path":"imbDRL/utils.py","file_url":"https://github.com/Denbergvanthijs/imbDRL/blob/HEAD/imbDRL/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"318d9a939851a219"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}