{"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/sim-to-real-reinforcement-learning-for","title":"Sim-to-Real Reinforcement Learning for Deformable Object Manipulation","arxiv_id":"1806.07851","date":"2018-06-20","proceeding":null,"authors":["Jan Matas","Stephen James","Andrew J. Davison"],"abstract":"We have seen much recent progress in rigid object manipulation, but\ninteraction with deformable objects has notably lagged behind. Due to the large\nconfiguration space of deformable objects, solutions using traditional\nmodelling approaches require significant engineering work. Perhaps then,\nbypassing the need for explicit modelling and instead learning the control in\nan end-to-end manner serves as a better approach? Despite the growing interest\nin the use of end-to-end robot learning approaches, only a small amount of work\nhas focused on their applicability to deformable object manipulation. Moreover,\ndue to the large amount of data needed to learn these end-to-end solutions, an\nemerging trend is to learn control policies in simulation and then transfer\nthem over to the real world. To-date, no work has explored whether it is\npossible to learn and transfer deformable object policies. We believe that if\nsim-to-real methods are to be employed further, then it should be possible to\nlearn to interact with a wide variety of objects, and not only rigid objects.\nIn this work, we use a combination of state-of-the-art deep reinforcement\nlearning algorithms to solve the problem of manipulating deformable objects\n(specifically cloth). We evaluate our approach on three tasks --- folding a\ntowel up to a mark, folding a face towel diagonally, and draping a piece of\ncloth over a hanger. Our agents are fully trained in simulation with domain\nrandomisation, and then successfully deployed in the real world without having\nseen any real deformable objects.","url_abs":"http://arxiv.org/abs/1806.07851v2","url_pdf":"http://arxiv.org/pdf/1806.07851v2.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":"sim-to-real-reinforcement-learning-for","repo_url":"https://github.com/JanMatas/Rainbow_ddpg","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"deformable-object-manipulation","task_name":"Deformable Object Manipulation"},{"task_slug":"object","task_name":"Object"},{"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=1806.07851","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.07851"}},"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/JanMatas/Rainbow_ddpg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":1,"unverified":5},"by_repo_kind":{"official":{"samples":7,"ran":2,"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":"6dd69b9b76d320b4","entry":"array_min2d","repo":"JanMatas/Rainbow_ddpg","repo_kind":"official","path":"rainbow_ddpg/prioritized_memory.py","file_url":"https://github.com/JanMatas/Rainbow_ddpg/blob/HEAD/rainbow_ddpg/prioritized_memory.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6dd69b9b76d320b4"}},{"code_sha256_prefix":"6eb59c36d3f33fe4","entry":"goal_distance","repo":"JanMatas/Rainbow_ddpg","repo_kind":"official","path":"micoenv/mico_robot_env.py","file_url":"https://github.com/JanMatas/Rainbow_ddpg/blob/HEAD/micoenv/mico_robot_env.py","link_basis":"plan_row","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":"6eb59c36d3f33fe4"}},{"code_sha256_prefix":"a17c64ee65bc3e66","entry":"createAndSave","repo":"JanMatas/Rainbow_ddpg","repo_kind":"official","path":"micoenv/perlin_noise.py","file_url":"https://github.com/JanMatas/Rainbow_ddpg/blob/HEAD/micoenv/perlin_noise.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":"a17c64ee65bc3e66"}},{"code_sha256_prefix":"eff73e9c174d66ee","entry":"createPalette","repo":"JanMatas/Rainbow_ddpg","repo_kind":"official","path":"micoenv/perlin_noise.py","file_url":"https://github.com/JanMatas/Rainbow_ddpg/blob/HEAD/micoenv/perlin_noise.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":"eff73e9c174d66ee"}},{"code_sha256_prefix":"00277beee4c6e0a9","entry":"denormalize","repo":"JanMatas/Rainbow_ddpg","repo_kind":"official","path":"rainbow_ddpg/ddpg.py","file_url":"https://github.com/JanMatas/Rainbow_ddpg/blob/HEAD/rainbow_ddpg/ddpg.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":"00277beee4c6e0a9"}},{"code_sha256_prefix":"2939760c5b7b44ae","entry":"normalize","repo":"JanMatas/Rainbow_ddpg","repo_kind":"official","path":"rainbow_ddpg/ddpg.py","file_url":"https://github.com/JanMatas/Rainbow_ddpg/blob/HEAD/rainbow_ddpg/ddpg.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":"2939760c5b7b44ae"}},{"code_sha256_prefix":"955e88fe58fc905a","entry":"reduce_std","repo":"JanMatas/Rainbow_ddpg","repo_kind":"official","path":"rainbow_ddpg/ddpg.py","file_url":"https://github.com/JanMatas/Rainbow_ddpg/blob/HEAD/rainbow_ddpg/ddpg.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":"955e88fe58fc905a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}