{"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/actor-mimic-deep-multitask-and-transfer","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","arxiv_id":"1511.06342","date":"2015-11-19","proceeding":null,"authors":["Emilio Parisotto","Jimmy Lei Ba","Ruslan Salakhutdinov"],"abstract":"The ability to act in multiple environments and transfer previous knowledge\nto new situations can be considered a critical aspect of any intelligent agent.\nTowards this goal, we define a novel method of multitask and transfer learning\nthat enables an autonomous agent to learn how to behave in multiple tasks\nsimultaneously, and then generalize its knowledge to new domains. This method,\ntermed \"Actor-Mimic\", exploits the use of deep reinforcement learning and model\ncompression techniques to train a single policy network that learns how to act\nin a set of distinct tasks by using the guidance of several expert teachers. We\nthen show that the representations learnt by the deep policy network are\ncapable of generalizing to new tasks with no prior expert guidance, speeding up\nlearning in novel environments. Although our method can in general be applied\nto a wide range of problems, we use Atari games as a testing environment to\ndemonstrate these methods.","url_abs":"http://arxiv.org/abs/1511.06342v4","url_pdf":"http://arxiv.org/pdf/1511.06342v4.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":"actor-mimic-deep-multitask-and-transfer","repo_url":"https://github.com/andris955/diplomaterv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"actor-mimic-deep-multitask-and-transfer","repo_url":"https://github.com/eparisotto/ActorMimic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"torch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"actor-mimic-deep-multitask-and-transfer","repo_url":"https://github.com/tophatraptor/si-transfer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"atari-games","task_name":"Atari Games"},{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"model-compression","task_name":"Model Compression"},{"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":"transfer-reinforcement-learning","task_name":"Transfer Reinforcement Learning"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.06342","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}