{"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-in-parameterized","title":"Deep Reinforcement Learning in Parameterized Action Space","arxiv_id":"1511.04143","date":"2015-11-13","proceeding":null,"authors":["Matthew Hausknecht","Peter Stone"],"abstract":"Recent work has shown that deep neural networks are capable of approximating both value functions and policies in reinforcement learning domains featuring continuous state and action spaces. However, to the best of our knowledge no previous work has succeeded at using deep neural networks in structured (parameterized) continuous action spaces. To fill this gap, this paper focuses on learning within the domain of simulated RoboCup soccer, which features a small set of discrete action types, each of which is parameterized with continuous variables. The best learned agent can score goals more reliably than the 2012 RoboCup champion agent. As such, this paper represents a successful extension of deep reinforcement learning to the class of parameterized action space MDPs.","url_abs":"https://arxiv.org/abs/1511.04143v5","url_pdf":"https://arxiv.org/pdf/1511.04143v5.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-in-parameterized","repo_url":"https://github.com/mhauskn/dqn-hfo","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-in-parameterized","repo_url":"https://github.com/MLCS-Yonsei/ddpg-control","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-in-parameterized","repo_url":"https://github.com/cycraig/MP-DQN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-in-parameterized","repo_url":"https://github.com/ltzheng/pddpg-hfo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-reinforcement-learning-in-parameterized","repo_url":"https://github.com/opendilab/DI-engine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"deep-reinforcement-learning-in-parameterized","repo_url":"https://github.com/stevenpjg/ddpg-aigym","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-reinforcement-learning-in-parameterized","repo_url":"https://github.com/thainv0212/re-ddpg","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":"https://app.syntology.ai/?focus=1511.04143","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.04143"}},"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/cycraig/MP-DQN","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thainv0212/re-ddpg","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ltzheng/pddpg-hfo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mhauskn/dqn-hfo","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MLCS-Yonsei/ddpg-control","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stevenpjg/ddpg-aigym","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/opendilab/DI-engine","reach":null}],"summary":{"ran_honours":1,"ran_fixture":1},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":"4acf2a2c58e59260","entry":"evaluate","repo":"cycraig/MP-DQN","repo_kind":"listed","path":"run_soccer_pdqn.py","file_url":"https://github.com/cycraig/MP-DQN/blob/HEAD/run_soccer_pdqn.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4acf2a2c58e59260"}},{"code_sha256_prefix":"f114c00ceb748082","entry":"pad_action","repo":"cycraig/MP-DQN","repo_kind":"listed","path":"run_soccer_pdqn.py","file_url":"https://github.com/cycraig/MP-DQN/blob/HEAD/run_soccer_pdqn.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f114c00ceb748082"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}