{"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/action-depedent-control-variates-for-policy","title":"Action-depedent Control Variates for Policy Optimization via Stein's Identity","arxiv_id":"1710.11198","date":"2017-10-30","proceeding":null,"authors":["Hao Liu","Yihao Feng","Yi Mao","Dengyong Zhou","Jian Peng","Qiang Liu"],"abstract":"Policy gradient methods have achieved remarkable successes in solving\nchallenging reinforcement learning problems. However, it still often suffers\nfrom the large variance issue on policy gradient estimation, which leads to\npoor sample efficiency during training. In this work, we propose a control\nvariate method to effectively reduce variance for policy gradient methods.\nMotivated by the Stein's identity, our method extends the previous control\nvariate methods used in REINFORCE and advantage actor-critic by introducing\nmore general action-dependent baseline functions. Empirical studies show that\nour method significantly improves the sample efficiency of the state-of-the-art\npolicy gradient approaches.","url_abs":"http://arxiv.org/abs/1710.11198v4","url_pdf":"http://arxiv.org/pdf/1710.11198v4.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":"action-depedent-control-variates-for-policy","repo_url":"https://github.com/DartML/PPO-Stein-Control-Variate","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"action-depedent-control-variates-for-policy","repo_url":"https://github.com/brain-research/mirage-rl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"policy-gradient-methods","task_name":"Policy Gradient Methods"},{"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":[{"method_slug":"reinforce","method_name":"REINFORCE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1710.11198","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.11198"}},"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/brain-research/mirage-rl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/DartML/PPO-Stein-Control-Variate","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"listed":{"samples":7,"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":"f397f62536003e67","entry":"gen_index","repo":"DartML/PPO-Stein-Control-Variate","repo_kind":"listed","path":"evaluation/traj_visualize.py","file_url":"https://github.com/DartML/PPO-Stein-Control-Variate/blob/HEAD/evaluation/traj_visualize.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":"f397f62536003e67"}},{"code_sha256_prefix":"ff04b3ceca88b830","entry":"init_gym","repo":"DartML/PPO-Stein-Control-Variate","repo_kind":"listed","path":"evaluation/main_algo.py","file_url":"https://github.com/DartML/PPO-Stein-Control-Variate/blob/HEAD/evaluation/main_algo.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":"ff04b3ceca88b830"}},{"code_sha256_prefix":"11dad5a70711db44","entry":"init_gym","repo":"DartML/PPO-Stein-Control-Variate","repo_kind":"listed","path":"optimization/main_algo.py","file_url":"https://github.com/DartML/PPO-Stein-Control-Variate/blob/HEAD/optimization/main_algo.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":"11dad5a70711db44"}},{"code_sha256_prefix":"ec6862dc1b375e0c","entry":"load_sample_grads","repo":"DartML/PPO-Stein-Control-Variate","repo_kind":"listed","path":"evaluation/traj_visualize.py","file_url":"https://github.com/DartML/PPO-Stein-Control-Variate/blob/HEAD/evaluation/traj_visualize.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":"ec6862dc1b375e0c"}},{"code_sha256_prefix":"071e746ec3f03d74","entry":"make_output_format","repo":"DartML/PPO-Stein-Control-Variate","repo_kind":"listed","path":"evaluation/tb_logger.py","file_url":"https://github.com/DartML/PPO-Stein-Control-Variate/blob/HEAD/evaluation/tb_logger.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":"071e746ec3f03d74"}},{"code_sha256_prefix":"fe515a034e675f33","entry":"run_episode","repo":"DartML/PPO-Stein-Control-Variate","repo_kind":"listed","path":"evaluation/main_algo.py","file_url":"https://github.com/DartML/PPO-Stein-Control-Variate/blob/HEAD/evaluation/main_algo.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":"fe515a034e675f33"}},{"code_sha256_prefix":"d65e0044847c6ca7","entry":"run_episode","repo":"DartML/PPO-Stein-Control-Variate","repo_kind":"listed","path":"optimization/main_algo.py","file_url":"https://github.com/DartML/PPO-Stein-Control-Variate/blob/HEAD/optimization/main_algo.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":"d65e0044847c6ca7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}