{"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/residual-policy-learning","title":"Residual Policy Learning","arxiv_id":"1812.06298","date":"2018-12-15","proceeding":null,"authors":["Tom Silver","Kelsey Allen","Josh Tenenbaum","Leslie Kaelbling"],"abstract":"We present Residual Policy Learning (RPL): a simple method for improving\nnondifferentiable policies using model-free deep reinforcement learning. RPL\nthrives in complex robotic manipulation tasks where good but imperfect\ncontrollers are available. In these tasks, reinforcement learning from scratch\nremains data-inefficient or intractable, but learning a residual on top of the\ninitial controller can yield substantial improvements. We study RPL in six\nchallenging MuJoCo tasks involving partial observability, sensor noise, model\nmisspecification, and controller miscalibration. For initial controllers, we\nconsider both hand-designed policies and model-predictive controllers with\nknown or learned transition models. By combining learning with control\nalgorithms, RPL can perform long-horizon, sparse-reward tasks for which\nreinforcement learning alone fails. Moreover, we find that RPL consistently and\nsubstantially improves on the initial controllers. We argue that RPL is a\npromising approach for combining the complementary strengths of deep\nreinforcement learning and robotic control, pushing the boundaries of what\neither can achieve independently. Video and code at\nhttps://k-r-allen.github.io/residual-policy-learning/.","url_abs":"http://arxiv.org/abs/1812.06298v2","url_pdf":"http://arxiv.org/pdf/1812.06298v2.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":"residual-policy-learning","repo_url":"https://github.com/k-r-allen/residual-policy-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"mujoco","task_name":"MuJoCo"},{"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=1812.06298","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1812.06298"}},"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/k-r-allen/residual-policy-learning","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"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":1,"samples":[{"code_sha256_prefix":"d7f89832be19bfa8","entry":"load_policy","repo":"k-r-allen/residual-policy-learning","repo_kind":"listed","path":"tensorflow/experiment/train_residual_base.py","file_url":"https://github.com/k-r-allen/residual-policy-learning/blob/HEAD/tensorflow/experiment/train_residual_base.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d7f89832be19bfa8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}