{"id":"W4385729101","doi":"10.1016/j.ins.2023.119481","title":"Reward shaping using convolutional neural network","year":2023,"lang":"en","type":"article","venue":"Information Sciences","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Markov decision process; Reinforcement learning; Convolutional neural network; Stochastic matrix; Representation (politics); Convolution (computer science); Artificial intelligence; Matrix (chemical analysis); Function (biology); Markov chain; Bellman equation; Algorithm; Artificial neural network; Markov process; Machine learning; Mathematical optimization; Mathematics; 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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001118904,0.00007925187,0.00007719127,0.0002349612,0.0006526841,0.0006398838,0.0008292974,0.0000325954,0.00001799436],"category_scores_gemma":[0.0001368859,0.00007138437,0.00003589155,0.002045089,0.0001472532,0.005117549,0.0003005622,0.00008608896,0.0005075623],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004090004,"about_ca_system_score_gemma":0.0001374283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001674913,"about_ca_topic_score_gemma":5.199238e-7,"domain_scores_codex":[0.998474,0.00003210565,0.0003232408,0.00012391,0.0006809008,0.0003658675],"domain_scores_gemma":[0.9993793,0.000112444,0.0001809483,0.0001717091,0.0001000714,0.00005555179],"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":[3.954019e-7,4.411947e-7,0.001530057,0.000003521409,0.000001638392,4.064145e-7,0.0003871719,0.9694937,0.000009187403,0.02513359,0.001445677,0.001994187],"study_design_scores_gemma":[0.00006860441,0.00002269871,0.004703509,0.00001401997,9.114785e-7,0.000009371443,0.00009180405,0.9880069,0.0000114749,0.0007492065,0.00622582,0.00009566577],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01814505,0.00001136073,0.9736726,0.0007472765,0.001127171,0.00009504554,5.391678e-7,0.0004189201,0.005782017],"genre_scores_gemma":[0.9529281,0.000007130563,0.0454482,0.001337666,0.000142032,0.000005111736,0.000008024496,0.000002581673,0.0001211794],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.934783,"threshold_uncertainty_score":0.6523856,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1262881818370389,"score_gpt":0.3253652114570306,"score_spread":0.1990770296199917,"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."}}