{"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/collaborative-deep-reinforcement-learning","title":"Collaborative Deep Reinforcement Learning","arxiv_id":"1702.05796","date":"2017-02-19","proceeding":null,"authors":["Kaixiang Lin","Shu Wang","Jiayu Zhou"],"abstract":"Besides independent learning, human learning process is highly improved by\nsummarizing what has been learned, communicating it with peers, and\nsubsequently fusing knowledge from different sources to assist the current\nlearning goal. This collaborative learning procedure ensures that the knowledge\nis shared, continuously refined, and concluded from different perspectives to\nconstruct a more profound understanding. The idea of knowledge transfer has led\nto many advances in machine learning and data mining, but significant\nchallenges remain, especially when it comes to reinforcement learning,\nheterogeneous model structures, and different learning tasks. Motivated by\nhuman collaborative learning, in this paper we propose a collaborative deep\nreinforcement learning (CDRL) framework that performs adaptive knowledge\ntransfer among heterogeneous learning agents. Specifically, the proposed CDRL\nconducts a novel deep knowledge distillation method to address the\nheterogeneity among different learning tasks with a deep alignment network.\nFurthermore, we present an efficient collaborative Asynchronous Advantage\nActor-Critic (cA3C) algorithm to incorporate deep knowledge distillation into\nthe online training of agents, and demonstrate the effectiveness of the CDRL\nframework using extensive empirical evaluation on OpenAI gym.","url_abs":"http://arxiv.org/abs/1702.05796v1","url_pdf":"http://arxiv.org/pdf/1702.05796v1.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":"collaborative-deep-reinforcement-learning","repo_url":"https://github.com/illidanlab/cdrl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.05796","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}