{"id":"W7124264120","doi":"10.65109/zliw2815","title":"Mastering Robot Control through Point-based Reinforcement Learning with Pre-training","year":2024,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Robustness (evolution); Robot; Leverage (statistics); Robotics; Limiting; Rendering (computer graphics)","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","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001567688,0.001110811,0.000918604,0.0004340371,0.0007983829,0.004067766,0.001614662,0.0002984981,0.001463433],"category_scores_gemma":[0.0001672003,0.0009536633,0.0003616775,0.001498031,0.0003361278,0.002142187,0.0005822909,0.001852083,0.0006113015],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004821446,"about_ca_system_score_gemma":0.001153306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001203443,"about_ca_topic_score_gemma":0.000008436053,"domain_scores_codex":[0.9922745,0.0003485208,0.001569231,0.001834007,0.001917907,0.002055878],"domain_scores_gemma":[0.9966751,0.0008000341,0.0004747813,0.001374316,0.0002794819,0.0003962922],"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":[0.0001362347,0.00002488041,0.0002437124,0.0006207398,0.0004419515,0.0002910868,0.008985128,0.9560623,0.000498871,0.01428635,0.0001660497,0.01824272],"study_design_scores_gemma":[0.00221499,0.002766353,0.00009771789,0.00286303,0.000210721,0.00009695398,0.0007322904,0.9749413,0.0006543192,0.0000521232,0.01412901,0.001241181],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0003301458,0.0006699251,0.9552434,0.002921948,0.001865029,0.001219523,9.762961e-7,0.001607773,0.03614128],"genre_scores_gemma":[0.878792,0.00004568715,0.09546883,0.0013932,0.0003597558,0.0000771665,0.00001174043,0.0001489901,0.02370257],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8784619,"threshold_uncertainty_score":0.9994494,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02640634819717081,"score_gpt":0.2616624150467427,"score_spread":0.2352560668495719,"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."}}