{"id":"W4400459471","doi":"10.1007/s10846-024-02118-y","title":"Deep Model-Based Reinforcement Learning for Predictive Control of Robotic Systems with Dense and Sparse Rewards","year":2024,"lang":"en","type":"article","venue":"Journal of Intelligent & Robotic Systems","topic":"Advanced Control Systems Optimization","field":"Engineering","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Task (project management); Machine learning; Model predictive control; Robotics; Sample (material); Field (mathematics); Bellman equation; Robot; Binary classification; Control (management); Mathematical optimization; Engineering; Support vector machine; Mathematics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008384904,0.0003250777,0.0009310129,0.0004019892,0.0000606125,0.0001405114,0.000160198,0.0001357763,0.000001799058],"category_scores_gemma":[0.000138045,0.000253864,0.0001672649,0.0002173573,0.00004940026,0.0002951845,0.00001074808,0.0002976506,0.000001919988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004530942,"about_ca_system_score_gemma":0.0001334338,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001655183,"about_ca_topic_score_gemma":0.00000268618,"domain_scores_codex":[0.9973624,0.0001089455,0.001450156,0.000216638,0.0005241379,0.0003377732],"domain_scores_gemma":[0.9979461,0.0004526333,0.0005518744,0.0002043053,0.0006687909,0.0001763115],"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":[0.0002781111,0.00001779092,0.0001415235,0.002353245,0.0007296826,0.00002766458,0.0004600922,0.9948013,0.0004637611,0.0004808521,0.00004044214,0.0002055087],"study_design_scores_gemma":[0.001129189,0.0009227926,0.000006141583,0.003874931,0.0004768523,0.0002534109,0.000802062,0.9920337,0.0001770429,0.00001662455,0.00007897879,0.0002282598],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008119161,0.01768111,0.9783198,0.00002157873,0.00164845,0.001332335,0.000002856382,0.0001014147,0.00008049572],"genre_scores_gemma":[0.9961591,0.0001774649,0.002993966,0.000005254661,0.0003020794,0.00009340188,0.000004643591,0.00009553027,0.000168552],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9953472,"threshold_uncertainty_score":0.9999914,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01113539873541915,"score_gpt":0.2244118147702045,"score_spread":0.2132764160347854,"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."}}