{"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/modular-multi-objective-deep-reinforcement","title":"Modular Multi-Objective Deep Reinforcement Learning with Decision Values","arxiv_id":"1704.06676","date":"2017-04-21","proceeding":null,"authors":["Tomasz Tajmajer"],"abstract":"In this work we present a method for using Deep Q-Networks (DQNs) in\nmulti-objective environments. Deep Q-Networks provide remarkable performance in\nsingle objective problems learning from high-level visual state\nrepresentations. However, in many scenarios (e.g in robotics, games), the agent\nneeds to pursue multiple objectives simultaneously. We propose an architecture\nin which separate DQNs are used to control the agent's behaviour with respect\nto particular objectives. In this architecture we introduce decision values to\nimprove the scalarization of multiple DQNs into a single action. Our\narchitecture enables the decomposition of the agent's behaviour into\ncontrollable and replaceable sub-behaviours learned by distinct modules.\nMoreover, it allows to change the priorities of particular objectives\npost-learning, while preserving the overall performance of the agent. To\nevaluate our solution we used a game-like simulator in which an agent -\nprovided with high-level visual input - pursues multiple objectives in a 2D\nworld.","url_abs":"http://arxiv.org/abs/1704.06676v2","url_pdf":"http://arxiv.org/pdf/1704.06676v2.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":"modular-multi-objective-deep-reinforcement","repo_url":"https://github.com/ttajmajer/morl-dv","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}