{"id":"W4377018773","doi":"10.32473/flairs.36.133317","title":"Evaluation of Techniques for Sim2Real Reinforcement Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ... International Florida Artificial Intelligence Research Society Conference","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Reinforcement learning; Computer science; Bridging (networking); Bridge (graph theory); Generalization; Noise (video); Domain (mathematical analysis); Human–computer interaction; Transfer of learning; Process (computing); Artificial intelligence; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.01198714,0.000153167,0.0002006287,0.0002352001,0.0003384382,0.0002606954,0.002935859,0.0001078452,0.00004510781],"category_scores_gemma":[0.004364729,0.000129172,0.0002602759,0.001312617,0.0003557846,0.0005899029,0.001169859,0.0004708591,0.00001903057],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003086101,"about_ca_system_score_gemma":0.0004924182,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005510717,"about_ca_topic_score_gemma":0.000002431155,"domain_scores_codex":[0.9944324,0.00005535708,0.0007108808,0.0004081477,0.003930742,0.0004624391],"domain_scores_gemma":[0.9883778,0.0005529157,0.0004215579,0.0002397228,0.01034383,0.00006416006],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003817395,0.0000420232,0.0003727943,0.0001391192,0.0001646087,8.629897e-8,0.004408824,0.1983682,0.08783665,0.6414411,0.002633905,0.06455453],"study_design_scores_gemma":[0.00003354614,0.0001211914,0.00004775445,0.0001152546,0.00001181921,4.474741e-7,0.001441645,0.6604279,0.2939756,0.0431373,0.0006055086,0.00008213164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03162128,0.00001972297,0.9435728,0.004976011,0.001013546,0.002012042,0.000005650845,0.0002668033,0.01651212],"genre_scores_gemma":[0.9914294,0.000132091,0.007120717,0.00002130541,0.0001769791,0.00022323,0.000006317567,0.00001362988,0.0008763621],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9598081,"threshold_uncertainty_score":0.5455606,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2601722272290781,"score_gpt":0.4271582699048349,"score_spread":0.1669860426757567,"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."}}