{"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/clipped-action-policy-gradient","title":"Clipped Action Policy Gradient","arxiv_id":"1802.07564","date":"2018-02-21","proceeding":"ICML 2018 7","authors":["Yasuhiro Fujita","Shin-ichi Maeda"],"abstract":"Many continuous control tasks have bounded action spaces. When policy\ngradient methods are applied to such tasks, out-of-bound actions need to be\nclipped before execution, while policies are usually optimized as if the\nactions are not clipped. We propose a policy gradient estimator that exploits\nthe knowledge of actions being clipped to reduce the variance in estimation. We\nprove that our estimator, named clipped action policy gradient (CAPG), is\nunbiased and achieves lower variance than the conventional estimator that\nignores action bounds. Experimental results demonstrate that CAPG generally\noutperforms the conventional estimator, indicating that it is a better policy\ngradient estimator for continuous control tasks. The source code is available\nat https://github.com/pfnet-research/capg.","url_abs":"http://arxiv.org/abs/1802.07564v2","url_pdf":"http://arxiv.org/pdf/1802.07564v2.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":"clipped-action-policy-gradient","repo_url":"https://github.com/pfnet-research/capg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"continuous-control","task_name":"Continuous Control"},{"task_slug":"policy-gradient-methods","task_name":"Policy Gradient Methods"},{"task_slug":"continuous-control","task_name":"continuous-control"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.07564","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1802.07564"}},"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/pfnet-research/capg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"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":"5f86c30a0e558994","entry":"elementwise_gaussian_log_pdf","repo":"pfnet-research/capg","repo_kind":"official","path":"clipped_gaussian.py","file_url":"https://github.com/pfnet-research/capg/blob/HEAD/clipped_gaussian.py","link_basis":"first_harvest_node","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":"5f86c30a0e558994"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}