{"id":"W4310849374","doi":"10.1016/j.autcon.2022.104691","title":"To imitate or not to imitate: Boosting reinforcement learning-based construction robotic control for long-horizon tasks using virtual demonstrations","year":2022,"lang":"en","type":"article","venue":"Automation in Construction","topic":"Innovations in Concrete and Construction Materials","field":"Engineering","cited_by":56,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Reinforcement learning; Teleoperation; Boosting (machine learning); Robot; Computer science; Artificial intelligence; Adaptability; Control (management); Human–computer interaction; Machine learning; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007285848,0.000327256,0.0003946908,0.001077012,0.0008736643,0.0001854728,0.0001768733,0.0001255048,0.0003294474],"category_scores_gemma":[0.0003603352,0.0003983611,0.00009172279,0.001366628,0.00008893526,0.0004547146,0.00004811942,0.0003146773,0.00002234869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008848088,"about_ca_system_score_gemma":0.0002674282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002959987,"about_ca_topic_score_gemma":0.00002270915,"domain_scores_codex":[0.9972656,0.0001811949,0.001211011,0.0004410665,0.000422105,0.0004790364],"domain_scores_gemma":[0.9987151,0.0002911691,0.0002840459,0.0002769522,0.0003197463,0.0001129766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002591804,0.000008598668,0.0006210052,0.00005064518,0.00004606366,0.000002667481,0.0001390618,0.9462156,0.03146818,0.002779061,0.0002174339,0.01819249],"study_design_scores_gemma":[0.002093192,0.0005669806,0.0007457461,0.00008855785,0.0000807976,0.0001878447,0.001907399,0.976312,0.01639196,0.0001130457,0.0009264516,0.0005860303],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3599257,0.000003412895,0.6353828,0.0002301302,0.002611942,0.001230762,0.00004451693,0.0004593577,0.0001113971],"genre_scores_gemma":[0.9169019,0.000001831733,0.081614,0.000236706,0.0001878925,0.000794346,0.0001508505,0.00005998573,0.00005250667],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5569762,"threshold_uncertainty_score":0.9998468,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02382609092479164,"score_gpt":0.2690324045061778,"score_spread":0.2452063135813861,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}