{"id":"W7000794688","doi":"","title":"Hard attention finding using reinforcement learning","year":2025,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Reinforcement; Control (management); Action (physics); Matching (statistics)","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":[0.0007728479,0.0007515043,0.0009194967,0.0004610318,0.0005327996,0.001047248,0.001310685,0.0007809113,0.008251762],"category_scores_gemma":[0.004947634,0.0003239386,0.0004061539,0.0002895159,0.0005649288,0.001187179,0.001531128,0.001957943,0.001304977],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008130966,"about_ca_system_score_gemma":0.0008249647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005325826,"about_ca_topic_score_gemma":0.004696317,"domain_scores_codex":[0.9995393,0.0001066511,0.00001862688,0.0001607985,0.0001030021,0.00007177486],"domain_scores_gemma":[0.9981394,0.00103089,0.0001073096,0.0001774063,0.0003339704,0.0002109889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001127196,0.0008901428,0.002780581,0.0001728608,0.0001353502,0.0001482228,0.0001605063,0.2143582,0.02669285,0.0115249,0.01949811,0.7225112],"study_design_scores_gemma":[0.00005881527,0.00009753266,0.0004501681,0.000008604105,0.00002156847,0.00002623882,0.00002040759,0.9875844,0.004339749,0.006288778,0.001093192,0.00001042472],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1503745,0.001099661,0.8224922,0.001655791,0.0008351362,0.0002244608,0.00009207056,0.004440682,0.01878538],"genre_scores_gemma":[0.8743337,0.0002180636,0.1087864,0.0002842014,0.0001612547,0.0001123591,0.0001145652,0.0002408373,0.01574863],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.008251762,"threshold_uncertainty_score":0.02760488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03451985705745916,"score_gpt":0.2720961607043954,"score_spread":0.2375763036469362,"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."}}