{"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/last-iterate-global-convergence-of-policy","title":"Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning","arxiv_id":"2407.10775","date":"2024-07-15","proceeding":null,"authors":["Alessandro Montenegro","Marco Mussi","Matteo Papini","Alberto Maria Metelli"],"abstract":"Constrained Reinforcement Learning (CRL) tackles sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints, which are often formulated as expected costs. In this setting, policy-based methods are widely used since they come with several advantages when dealing with continuous-control problems. These methods search in the policy space with an action-based or parameter-based exploration strategy, depending on whether they learn directly the parameters of a stochastic policy or those of a stochastic hyperpolicy. In this paper, we propose a general framework for addressing CRL problems via gradient-based primal-dual algorithms, relying on an alternate ascent/descent scheme with dual-variable regularization. We introduce an exploration-agnostic algorithm, called C-PG, which exhibits global last-iterate convergence guarantees under (weak) gradient domination assumptions, improving and generalizing existing results. Then, we design C-PGAE and C-PGPE, the action-based and the parameter-based versions of C-PG, respectively, and we illustrate how they naturally extend to constraints defined in terms of risk measures over the costs, as it is often requested in safety-critical scenarios. Finally, we numerically validate our algorithms on constrained control problems, and compare them with state-of-the-art baselines, demonstrating their effectiveness.","url_abs":"https://arxiv.org/abs/2407.10775v2","url_pdf":"https://arxiv.org/pdf/2407.10775v2.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":[],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"decision-making","task_name":"Decision Making"},{"task_slug":"sequential-decision-making","task_name":"Sequential Decision Making"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.10775","atlas_url":"https://app.syntology.ai/?focus=2407.10775","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.10775"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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":"deterministic:regex_extraction","url":"https://github.com/MontenegroAlessandro/MagicRL","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3},"by_repo_kind":{"found_in_text":{"samples":3,"ran":3,"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":"736ea1ebc2de88cd","entry":"is_numpy","repo":"MontenegroAlessandro/MagicRL","repo_kind":"found_in_text","path":"algorithms/utils.py","file_url":"https://github.com/MontenegroAlessandro/MagicRL/blob/HEAD/algorithms/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"736ea1ebc2de88cd"}},{"code_sha256_prefix":"93e3802d361f950d","entry":"is_tensor","repo":"MontenegroAlessandro/MagicRL","repo_kind":"found_in_text","path":"algorithms/utils.py","file_url":"https://github.com/MontenegroAlessandro/MagicRL/blob/HEAD/algorithms/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93e3802d361f950d"}},{"code_sha256_prefix":"6d76fa07dc298ca8","entry":"tensor_to_numpy","repo":"MontenegroAlessandro/MagicRL","repo_kind":"found_in_text","path":"algorithms/utils.py","file_url":"https://github.com/MontenegroAlessandro/MagicRL/blob/HEAD/algorithms/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d76fa07dc298ca8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}