{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001034072,0.0006336772,0.0005818551,0.0002242551,0.0002009039,0.0004286403,0.0008815406,0.0006715277,0.001117972],"category_scores_gemma":[0.003263152,0.0003046464,0.0002974283,0.0001705321,0.0006623529,0.0005211525,0.0009189791,0.0009690307,0.0001964786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005472857,"about_ca_system_score_gemma":0.001106846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002959915,"about_ca_topic_score_gemma":0.00247723,"domain_scores_codex":[0.9996958,0.000114486,0.00001378889,0.00005170036,0.00007026791,0.00005395988],"domain_scores_gemma":[0.9991998,0.0004898115,0.00008643972,0.00005469849,0.0001113069,0.00005791981],"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":[0.00008552823,0.00006501019,0.001010168,0.00005292711,0.0000305127,0.00005989248,0.00005291464,0.9507404,0.002164637,0.003938986,0.0006085297,0.04119044],"study_design_scores_gemma":[0.00000718507,0.00002973248,0.00005419152,0.000003538351,0.000002802688,0.000006906414,0.000002428429,0.998334,0.0003503043,0.001035869,0.0001709267,0.000002157314],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1053287,0.0005281955,0.8875141,0.0005218072,0.00008472982,0.00008228429,0.00002818861,0.0008133585,0.005098617],"genre_scores_gemma":[0.9329451,0.0001238131,0.06471291,0.0002181874,0.00001861484,0.00009387479,0.00003947716,0.00004920027,0.001798821],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002959915,"threshold_uncertainty_score":0.005885363,"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."}}