{"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/multi-pass-q-networks-for-deep-reinforcement","title":"Multi-Pass Q-Networks for Deep Reinforcement Learning with Parameterised Action Spaces","arxiv_id":"1905.04388","date":"2019-05-10","proceeding":null,"authors":["Craig J. Bester","Steven D. James","George D. Konidaris"],"abstract":"Parameterised actions in reinforcement learning are composed of discrete actions with continuous action-parameters. This provides a framework for solving complex domains that require combining high-level actions with flexible control. The recent P-DQN algorithm extends deep Q-networks to learn over such action spaces. However, it treats all action-parameters as a single joint input to the Q-network, invalidating its theoretical foundations. We analyse the issues with this approach and propose a novel method, multi-pass deep Q-networks, or MP-DQN, to address them. We empirically demonstrate that MP-DQN significantly outperforms P-DQN and other previous algorithms in terms of data efficiency and converged policy performance on the Platform, Robot Soccer Goal, and Half Field Offense domains.","url_abs":"https://arxiv.org/abs/1905.04388v1","url_pdf":"https://arxiv.org/pdf/1905.04388v1.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":"multi-pass-q-networks-for-deep-reinforcement","repo_url":"https://github.com/cycraig/MP-DQN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"multi-pass-q-networks-for-deep-reinforcement","repo_url":"https://github.com/cycraig/gym-goal","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-pass-q-networks-for-deep-reinforcement","repo_url":"https://github.com/cycraig/gym-platform","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"multi-pass-q-networks-for-deep-reinforcement","repo_url":"https://github.com/opendilab/DI-engine/blob/main/ding/policy/pdqn.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"control-with-prametrised-actions","task_name":"Control with Prametrised Actions"},{"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":[{"leaderboard":"/sota/control-with-prametrised-actions-on-half","task":"Control with Prametrised Actions","dataset":"Half Field Offence","model":"MP-DQN","rank_in_archive_order":1,"of":2,"metrics":{"Goal Probability":"0.913"},"uses_additional_data":false},{"leaderboard":"/sota/control-with-prametrised-actions-on-platform","task":"Control with Prametrised Actions","dataset":"Platform","model":"MP-DQN","rank_in_archive_order":1,"of":2,"metrics":{"Return":"0.987"},"uses_additional_data":false},{"leaderboard":"/sota/control-with-prametrised-actions-on-robot","task":"Control with Prametrised Actions","dataset":"Robot Soccer Goal","model":"MP-DQN","rank_in_archive_order":1,"of":2,"metrics":{"Goal Probability":"0.789"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1905.04388","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}