{"id":"W4414418856","doi":"10.23977/jaip.2025.080313","title":"Prioritized Reward of Deep Reinforcement Learning Applied Mobile Manipulation Reaching Tasks","year":2025,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Robot Manipulation and Learning","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Task (project management); Function (biology); Mobile robot; Mobile manipulator; Base (topology); Robot","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001334067,0.0001316203,0.0002754137,0.0003239753,0.0001136998,0.00007709005,0.0001622686,0.00009047412,0.0001162006],"category_scores_gemma":[0.001062909,0.0001360921,0.00009890024,0.0003820009,0.00002690575,0.0005449604,0.00002969144,0.0007041091,0.00002081204],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001354441,"about_ca_system_score_gemma":0.00004082135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001620144,"about_ca_topic_score_gemma":0.00000481351,"domain_scores_codex":[0.9981671,0.0001140033,0.001106723,0.0001053362,0.0003330241,0.0001737982],"domain_scores_gemma":[0.9983763,0.0005185366,0.0006051505,0.0001347654,0.0003113934,0.0000538199],"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":[0.0001755388,0.00002962331,0.00005317386,0.00005448136,0.00007263948,0.000005466716,0.001683946,0.8858616,0.01668927,0.006967347,0.00002495181,0.08838194],"study_design_scores_gemma":[0.0001251887,0.0001505768,0.0001516978,0.000175475,0.0001556057,0.00003004218,0.007934671,0.9464296,0.0348606,0.001409729,0.008374316,0.0002024754],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01656397,0.0002894913,0.9673498,0.0001077304,0.0005968604,0.0001831895,3.206238e-8,0.00005526824,0.0148536],"genre_scores_gemma":[0.9909361,0.0001445337,0.008632265,0.00004938821,0.000136161,0.000004572935,0.000002122941,0.00001721314,0.00007761794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9743721,"threshold_uncertainty_score":0.5549677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03294986184125855,"score_gpt":0.3167157270523156,"score_spread":0.2837658652110571,"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."}}