{"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/efficiently-combining-human-demonstrations","title":"Efficiently Combining Human Demonstrations and Interventions for Safe Training of Autonomous Systems in Real-Time","arxiv_id":"1810.11545","date":"2018-10-26","proceeding":null,"authors":["Vinicius G. Goecks","Gregory M. Gremillion","Vernon J. Lawhern","John Valasek","Nicholas R. Waytowich"],"abstract":"This paper investigates how to utilize different forms of human interaction\nto safely train autonomous systems in real-time by learning from both human\ndemonstrations and interventions. We implement two components of the\nCycle-of-Learning for Autonomous Systems, which is our framework for combining\nmultiple modalities of human interaction. The current effort employs human\ndemonstrations to teach a desired behavior via imitation learning, then\nleverages intervention data to correct for undesired behaviors produced by the\nimitation learner to teach novel tasks to an autonomous agent safely, after\nonly minutes of training. We demonstrate this method in an autonomous perching\ntask using a quadrotor with continuous roll, pitch, yaw, and throttle commands\nand imagery captured from a downward-facing camera in a high-fidelity simulated\nenvironment. Our method improves task completion performance for the same\namount of human interaction when compared to learning from demonstrations\nalone, while also requiring on average 32% less data to achieve that\nperformance. This provides evidence that combining multiple modes of human\ninteraction can increase both the training speed and overall performance of\npolicies for autonomous systems.","url_abs":"http://arxiv.org/abs/1810.11545v2","url_pdf":"http://arxiv.org/pdf/1810.11545v2.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":"efficiently-combining-human-demonstrations","repo_url":"https://github.com/viniciusguigo/complete_col","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"imitation-learning","task_name":"Imitation Learning"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.11545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.11545"}},"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/viniciusguigo/complete_col","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"2cb95d0b3539063b","entry":"denormalize","repo":"viniciusguigo/complete_col","repo_kind":"listed","path":"ddpg_col.py","file_url":"https://github.com/viniciusguigo/complete_col/blob/HEAD/ddpg_col.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":"2cb95d0b3539063b"}},{"code_sha256_prefix":"94869c6890722a50","entry":"normalize","repo":"viniciusguigo/complete_col","repo_kind":"listed","path":"ddpg_col.py","file_url":"https://github.com/viniciusguigo/complete_col/blob/HEAD/ddpg_col.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":"94869c6890722a50"}},{"code_sha256_prefix":"826b8176618996ff","entry":"tag_episode_reward_logger","repo":"viniciusguigo/complete_col","repo_kind":"listed","path":"ddpg_col.py","file_url":"https://github.com/viniciusguigo/complete_col/blob/HEAD/ddpg_col.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":"826b8176618996ff"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}