{"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/reinforcement-learning-with-parameterized","title":"Reinforcement Learning with Parameterized Actions","arxiv_id":"1509.01644","date":"2015-09-05","proceeding":null,"authors":["Warwick Masson","Pravesh Ranchod","George Konidaris"],"abstract":"We introduce a model-free algorithm for learning in Markov decision processes\nwith parameterized actions-discrete actions with continuous parameters. At each\nstep the agent must select both which action to use and which parameters to use\nwith that action. We introduce the Q-PAMDP algorithm for learning in these\ndomains, show that it converges to a local optimum, and compare it to direct\npolicy search in the goal-scoring and Platform domains.","url_abs":"http://arxiv.org/abs/1509.01644v4","url_pdf":"http://arxiv.org/pdf/1509.01644v4.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":"reinforcement-learning-with-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":"reinforcement-learning-with-parameterized","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":"reinforcement-learning-with-parameterized","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"}}],"tasks":[{"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=1509.01644","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1509.01644"}},"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/cycraig/gym-goal","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cycraig/gym-platform","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran_draft_wrong":1,"unverified":4},"by_repo_kind":{"listed":{"samples":6,"ran":2,"repositories":2}},"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":"a07358c3feddc64a","entry":"evaluate","repo":"cycraig/MP-DQN","repo_kind":"listed","path":"run_goal_pdqn.py","file_url":"https://github.com/cycraig/MP-DQN/blob/HEAD/run_goal_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":"a07358c3feddc64a"}},{"code_sha256_prefix":"01291f67c9d125d4","entry":"pad_action","repo":"cycraig/MP-DQN","repo_kind":"listed","path":"run_goal_pdqn.py","file_url":"https://github.com/cycraig/MP-DQN/blob/HEAD/run_goal_pdqn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01291f67c9d125d4"}},{"code_sha256_prefix":"d3156c39902cb0a0","entry":"angle_difference","repo":"cycraig/gym-goal","repo_kind":"listed","path":"gym_goal/envs/util.py","file_url":"https://github.com/cycraig/gym-goal/blob/HEAD/gym_goal/envs/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d3156c39902cb0a0"}},{"code_sha256_prefix":"5cade6842144e12c","entry":"bound","repo":"cycraig/gym-goal","repo_kind":"listed","path":"gym_goal/envs/util.py","file_url":"https://github.com/cycraig/gym-goal/blob/HEAD/gym_goal/envs/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cade6842144e12c"}},{"code_sha256_prefix":"636fc5d1bc7b45f9","entry":"bound_vector","repo":"cycraig/gym-goal","repo_kind":"listed","path":"gym_goal/envs/util.py","file_url":"https://github.com/cycraig/gym-goal/blob/HEAD/gym_goal/envs/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"636fc5d1bc7b45f9"}},{"code_sha256_prefix":"b2b2c2c929019580","entry":"norm","repo":"cycraig/gym-goal","repo_kind":"listed","path":"gym_goal/envs/goal_env.py","file_url":"https://github.com/cycraig/gym-goal/blob/HEAD/gym_goal/envs/goal_env.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b2b2c2c929019580"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}