{"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/model-based-reinforcement-learning-for-7","title":"Model-based Reinforcement Learning for Parameterized Action Spaces","arxiv_id":"2404.03037","date":"2024-04-03","proceeding":null,"authors":["Renhao Zhang","Haotian Fu","Yilin Miao","George Konidaris"],"abstract":"We propose a novel model-based reinforcement learning algorithm -- Dynamics Learning and predictive control with Parameterized Actions (DLPA) -- for Parameterized Action Markov Decision Processes (PAMDPs). The agent learns a parameterized-action-conditioned dynamics model and plans with a modified Model Predictive Path Integral control. We theoretically quantify the difference between the generated trajectory and the optimal trajectory during planning in terms of the value they achieved through the lens of Lipschitz Continuity. Our empirical results on several standard benchmarks show that our algorithm achieves superior sample efficiency and asymptotic performance than state-of-the-art PAMDP methods.","url_abs":"https://arxiv.org/abs/2404.03037v3","url_pdf":"https://arxiv.org/pdf/2404.03037v3.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":"model-based-reinforcement-learning-for-7","repo_url":"https://github.com/valarzz/dlpa","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"model-based-reinforcement-learning-for-7","repo_url":"https://github.com/valarzz/model-based-reinforcement-learning-for-parameterized-action-spaces","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"model-based-reinforcement-learning","task_name":"Model-based Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"model","task_name":"model"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.03037","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.03037"}},"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/valarzz/model-based-reinforcement-learning-for-parameterized-action-spaces","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/valarzz/dlpa","reach":{"status":"ok"}}],"summary":{"ran":5,"ran_honours":1,"ran_fixture":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":9,"ran":9,"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":9,"samples":[{"code_sha256_prefix":"305195e43ea54d1a","entry":"ce","repo":"valarzz/dlpa","repo_kind":"official","path":"utils.py","file_url":"https://github.com/valarzz/dlpa/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"305195e43ea54d1a"}},{"code_sha256_prefix":"cfae8747398da049","entry":"gumbel_softmax","repo":"valarzz/dlpa","repo_kind":"official","path":"models/model_utils.py","file_url":"https://github.com/valarzz/dlpa/blob/HEAD/models/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cfae8747398da049"}},{"code_sha256_prefix":"6aa6155903c761f7","entry":"gumbel_softmax_sample","repo":"valarzz/dlpa","repo_kind":"official","path":"models/model_utils.py","file_url":"https://github.com/valarzz/dlpa/blob/HEAD/models/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6aa6155903c761f7"}},{"code_sha256_prefix":"9910e2fc297f8665","entry":"identity","repo":"valarzz/dlpa","repo_kind":"official","path":"models/networks.py","file_url":"https://github.com/valarzz/dlpa/blob/HEAD/models/networks.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9910e2fc297f8665"}},{"code_sha256_prefix":"9925b7e4eb50dcae","entry":"l1","repo":"valarzz/dlpa","repo_kind":"official","path":"utils.py","file_url":"https://github.com/valarzz/dlpa/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9925b7e4eb50dcae"}},{"code_sha256_prefix":"8c6d7bf8521d9aaf","entry":"mlp","repo":"valarzz/dlpa","repo_kind":"official","path":"models/networks.py","file_url":"https://github.com/valarzz/dlpa/blob/HEAD/models/networks.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8c6d7bf8521d9aaf"}},{"code_sha256_prefix":"8d8f088c9186b5d4","entry":"mse","repo":"valarzz/dlpa","repo_kind":"official","path":"utils.py","file_url":"https://github.com/valarzz/dlpa/blob/HEAD/utils.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8d8f088c9186b5d4"}},{"code_sha256_prefix":"9f124ed96fbb6266","entry":"q","repo":"valarzz/dlpa","repo_kind":"official","path":"models/networks.py","file_url":"https://github.com/valarzz/dlpa/blob/HEAD/models/networks.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9f124ed96fbb6266"}},{"code_sha256_prefix":"ad9b1527ee7ba21d","entry":"sample_gumbel","repo":"valarzz/dlpa","repo_kind":"official","path":"models/model_utils.py","file_url":"https://github.com/valarzz/dlpa/blob/HEAD/models/model_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ad9b1527ee7ba21d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}