{"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/task-embedded-control-networks-for-few-shot","title":"Task-Embedded Control Networks for Few-Shot Imitation Learning","arxiv_id":"1810.03237","date":"2018-10-08","proceeding":null,"authors":["Stephen James","Michael Bloesch","Andrew J. Davison"],"abstract":"Much like humans, robots should have the ability to leverage knowledge from\npreviously learned tasks in order to learn new tasks quickly in new and\nunfamiliar environments. Despite this, most robot learning approaches have\nfocused on learning a single task, from scratch, with a limited notion of\ngeneralisation, and no way of leveraging the knowledge to learn other tasks\nmore efficiently. One possible solution is meta-learning, but many of the\nrelated approaches are limited in their ability to scale to a large number of\ntasks and to learn further tasks without forgetting previously learned ones.\nWith this in mind, we introduce Task-Embedded Control Networks, which employ\nideas from metric learning in order to create a task embedding that can be used\nby a robot to learn new tasks from one or more demonstrations. In the area of\nvisually-guided manipulation, we present simulation results in which we surpass\nthe performance of a state-of-the-art method when using only visual information\nfrom each demonstration. Additionally, we demonstrate that our approach can\nalso be used in conjunction with domain randomisation to train our few-shot\nlearning ability in simulation and then deploy in the real world without any\nadditional training. Once deployed, the robot can learn new tasks from a single\nreal-world demonstration.","url_abs":"http://arxiv.org/abs/1810.03237v1","url_pdf":"http://arxiv.org/pdf/1810.03237v1.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":"task-embedded-control-networks-for-few-shot","repo_url":"https://github.com/stepjam/TecNets","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"task-embedded-control-networks-for-few-shot","repo_url":"https://github.com/naruya/tecnets-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"task-embedded-control-networks-for-few-shot","repo_url":"https://github.com/stepjam/PyRep","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-imitation-learning","task_name":"Few-Shot Imitation Learning"},{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"metric-learning","task_name":"Metric Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1810.03237","atlas_url":"https://app.syntology.ai/?focus=1810.03237","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.03237"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/naruya/tecnets-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stepjam/PyRep","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stepjam/TecNets","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran_violates":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":"63fa2e40d3371df3","entry":"eval_success","repo":"naruya/tecnets-pytorch","repo_kind":"listed","path":"sim_test.py","file_url":"https://github.com/naruya/tecnets-pytorch/blob/HEAD/sim_test.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"63fa2e40d3371df3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}