{"id":"W4385299175","doi":"10.1109/tai.2023.3299252","title":"Facilitating Sim-to-Real by Intrinsic Stochasticity of Real-Time Simulation in Reinforcement Learning for Robot Manipulation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Computer science; Robot; Artificial intelligence; Heuristic; Robotics; Generalizability theory; Task (project management); Simulation; Engineering","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0006861479,0.0001998553,0.0002514574,0.0005408244,0.0002388137,0.000080486,0.0003725702,0.00009852189,0.00002854103],"category_scores_gemma":[0.0001813072,0.0002326467,0.00008487779,0.001347278,0.00004601113,0.0003531052,0.00001003582,0.0002414171,0.0002128493],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001846443,"about_ca_system_score_gemma":0.00005063827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002941448,"about_ca_topic_score_gemma":0.0000474696,"domain_scores_codex":[0.9977521,0.00009984797,0.0008481247,0.0004416392,0.0004510146,0.000407284],"domain_scores_gemma":[0.9978688,0.001326589,0.0002103418,0.0003141148,0.0001881006,0.00009210518],"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":[0.00006976756,0.00003750737,0.000008099282,0.00002649579,0.00001076581,6.940852e-7,0.001866811,0.9143103,0.01874237,0.0007778151,0.000006568636,0.06414279],"study_design_scores_gemma":[0.00006593091,0.0005304572,0.00007312468,0.0000619537,0.00000819666,2.068738e-7,0.0002368326,0.9576486,0.04080189,0.0003617856,0.00001449417,0.0001965317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02401933,7.319545e-7,0.9743639,0.0001186505,0.0003045996,0.000776987,0.00000416726,0.0002599171,0.000151708],"genre_scores_gemma":[0.9905654,0.00001071025,0.008782011,0.00002102703,0.0000250016,0.00007840394,0.00001597431,0.00001903567,0.0004824014],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9665461,"threshold_uncertainty_score":0.9487056,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06739551366683552,"score_gpt":0.3288240012675382,"score_spread":0.2614284876007027,"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."}}