{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002379408,0.0005206016,0.0004918299,0.0002696169,0.0002605474,0.0007682369,0.0008804859,0.0005929716,0.001475352],"category_scores_gemma":[0.01007528,0.0003472243,0.0004770606,0.0002238744,0.001636724,0.001308671,0.001348423,0.001383628,0.0002616155],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005800649,"about_ca_system_score_gemma":0.001020319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000772948,"about_ca_topic_score_gemma":0.0007448536,"domain_scores_codex":[0.9985329,0.0008056133,0.00007866725,0.0001671493,0.0003396544,0.0000760148],"domain_scores_gemma":[0.9939973,0.003862964,0.0008009524,0.0009074512,0.0002895627,0.0001417348],"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":[0.0002134679,0.0001220185,0.001457407,0.0001162274,0.00004402707,0.00008725602,0.0001301526,0.92083,0.01182896,0.03621661,0.0002866081,0.02866726],"study_design_scores_gemma":[0.00001581062,0.00007387058,0.000149175,0.000009677457,0.000006376127,0.00002743726,0.000008260975,0.9880784,0.003690742,0.007197446,0.0007344907,0.000008332073],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.029297,0.00009833808,0.9681777,0.0001333287,0.000026469,0.0000511716,0.00001361622,0.0004532132,0.001749186],"genre_scores_gemma":[0.8814804,0.0001423638,0.1173441,0.0001212546,0.00001959154,0.0001645588,0.00003822399,0.0001141113,0.0005754204],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002379408,"threshold_uncertainty_score":0.01258361,"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."}}