{"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/deep-reinforcement-learning-for-industrial","title":"Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewards","arxiv_id":"1906.05841","date":"2019-06-13","proceeding":null,"authors":["Gerrit Schoettler","Ashvin Nair","Jianlan Luo","Shikhar Bahl","Juan Aparicio Ojea","Eugen Solowjow","Sergey Levine"],"abstract":"Connector insertion and many other tasks commonly found in modern manufacturing settings involve complex contact dynamics and friction. Since it is difficult to capture related physical effects with first-order modeling, traditional control methods often result in brittle and inaccurate controllers, which have to be manually tuned. Reinforcement learning (RL) methods have been demonstrated to be capable of learning controllers in such environments from autonomous interaction with the environment, but running RL algorithms in the real world poses sample efficiency and safety challenges. Moreover, in practical real-world settings we cannot assume access to perfect state information or dense reward signals. In this paper, we consider a variety of difficult industrial insertion tasks with visual inputs and different natural reward specifications, namely sparse rewards and goal images. We show that methods that combine RL with prior information, such as classical controllers or demonstrations, can solve these tasks from a reasonable amount of real-world interaction.","url_abs":"https://arxiv.org/abs/1906.05841v2","url_pdf":"https://arxiv.org/pdf/1906.05841v2.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":"deep-reinforcement-learning-for-industrial","repo_url":"https://github.com/mizolotu/SmartExcavator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"friction","task_name":"Friction"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.05841","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.05841"}},"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/mizolotu/SmartExcavator","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"ran_draft_wrong":1,"unverified":11},"by_repo_kind":{"listed":{"samples":13,"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":13,"samples":[{"code_sha256_prefix":"bcd8b4acab199405","entry":"make_output_format","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"baselines/logger.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/baselines/logger.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"bcd8b4acab199405"}},{"code_sha256_prefix":"a44574392d168384","entry":"register","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"baselines/common/models.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/baselines/common/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a44574392d168384"}},{"code_sha256_prefix":"9f1afcb162e28be2","entry":"augment_data","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"select_demonstration.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/select_demonstration.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":false,"mcp_get_code":{"code_sha256":"9f1afcb162e28be2"}},{"code_sha256_prefix":"2bf5c781f8e4aad5","entry":"build_impala_cnn","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"baselines/common/models.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/baselines/common/models.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":false,"mcp_get_code":{"code_sha256":"2bf5c781f8e4aad5"}},{"code_sha256_prefix":"53bf4f7471caf4d1","entry":"get_mode","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"env_backend.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/env_backend.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":false,"mcp_get_code":{"code_sha256":"53bf4f7471caf4d1"}},{"code_sha256_prefix":"506539b39f74a526","entry":"get_target","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"env_backend.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/env_backend.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":false,"mcp_get_code":{"code_sha256":"506539b39f74a526"}},{"code_sha256_prefix":"f693c76093f5fbcc","entry":"pid_controls","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"env_backend.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/env_backend.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":false,"mcp_get_code":{"code_sha256":"f693c76093f5fbcc"}},{"code_sha256_prefix":"91a934c3d796a9d4","entry":"profile","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"baselines/logger.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/baselines/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":false,"mcp_get_code":{"code_sha256":"91a934c3d796a9d4"}},{"code_sha256_prefix":"88ef5a17fc986d9a","entry":"read_json","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"baselines/logger.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/baselines/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":false,"mcp_get_code":{"code_sha256":"88ef5a17fc986d9a"}},{"code_sha256_prefix":"895ca4b776fb6d6d","entry":"rolling_window","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"baselines/results_plotter.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/baselines/results_plotter.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":false,"mcp_get_code":{"code_sha256":"895ca4b776fb6d6d"}},{"code_sha256_prefix":"2e61652e60f58f2d","entry":"split_data","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"select_demonstration.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/select_demonstration.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":false,"mcp_get_code":{"code_sha256":"2e61652e60f58f2d"}},{"code_sha256_prefix":"4ab4ad5ff9820e39","entry":"ts2xy","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"baselines/results_plotter.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/baselines/results_plotter.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":false,"mcp_get_code":{"code_sha256":"4ab4ad5ff9820e39"}},{"code_sha256_prefix":"43741b9339bd80da","entry":"window_func","repo":"mizolotu/SmartExcavator","repo_kind":"listed","path":"baselines/results_plotter.py","file_url":"https://github.com/mizolotu/SmartExcavator/blob/HEAD/baselines/results_plotter.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":false,"mcp_get_code":{"code_sha256":"43741b9339bd80da"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}