{"id":"W4407666659","doi":"10.1051/itmconf/20257301007","title":"Optimizing Robotic Arm Learning: Curiosity-Driven Deep Deterministic Policy Gradient","year":2025,"lang":"en","type":"article","venue":"ITM Web of Conferences","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs","funders":"","keywords":"Curiosity; Artificial intelligence; Computer science; Deep learning; Psychology; Human–computer interaction; Neuroscience","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":[0.0002424773,0.0002340029,0.0003987659,0.0005064252,0.0002146614,0.0002651955,0.001471779,0.00009535499,0.00003547387],"category_scores_gemma":[0.0004436029,0.0002238089,0.0001182591,0.000681583,0.0002047424,0.0002608454,0.000467405,0.0003215981,0.00002975281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006578508,"about_ca_system_score_gemma":0.00148873,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007445989,"about_ca_topic_score_gemma":0.00001860122,"domain_scores_codex":[0.9981087,0.0001439147,0.0005039679,0.0004130014,0.0003907501,0.0004396183],"domain_scores_gemma":[0.9984716,0.000384266,0.0003160833,0.0005211605,0.0002001152,0.000106774],"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":[0.000004790666,0.00004240264,0.006608731,0.00006121705,0.00005076457,0.000007934155,0.0006117565,0.6676418,0.0001858651,0.3185701,0.00003638608,0.006178261],"study_design_scores_gemma":[0.0003491732,0.0003196732,0.002551907,0.0002037507,0.00003299566,0.000004909316,0.0001310492,0.9883566,0.0007175651,0.002318525,0.004770936,0.0002428471],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005313616,0.0001317595,0.9241721,0.001043129,0.0005366243,0.0002001299,2.954201e-7,0.0001902207,0.0684121],"genre_scores_gemma":[0.9802594,0.00009688576,0.01798911,0.0001787351,0.00004561524,0.00001081472,0.000002798266,0.000007859134,0.001408779],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9749458,"threshold_uncertainty_score":0.9126661,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02139200815392064,"score_gpt":0.2807801220522062,"score_spread":0.2593881138982855,"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."}}