{"id":"W2060652090","doi":"10.1142/s0129183104006662","title":"REINFORCEMENT LEARNING WITH GOAL-DIRECTED ELIGIBILITY TRACES","year":2004,"lang":"en","type":"article","venue":"International Journal of Modern Physics C","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Reinforcement learning; TRACE (psycholinguistics); Computer science; Reinforcement; Artificial intelligence; Mechanism (biology); Machine learning; Psychology","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":[0.001050037,0.0005335548,0.0005816521,0.000291762,0.0002888938,0.0006142298,0.001344239,0.0007710444,0.001632248],"category_scores_gemma":[0.006544967,0.0002077321,0.000327703,0.0002899247,0.0008837685,0.001608341,0.001236827,0.001526774,0.0002335495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004325515,"about_ca_system_score_gemma":0.001247416,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001339054,"about_ca_topic_score_gemma":0.00128777,"domain_scores_codex":[0.999409,0.0002043602,0.00003734753,0.00009387072,0.000185306,0.00007030096],"domain_scores_gemma":[0.9981366,0.001079262,0.0001482974,0.0002199383,0.0002573132,0.0001585149],"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":[0.0004259458,0.0003007716,0.001121108,0.0001709665,0.00007163097,0.0002861526,0.000171558,0.5883097,0.01638613,0.2356854,0.001895299,0.1551754],"study_design_scores_gemma":[0.00005838377,0.00007667146,0.00009392048,0.000006184609,0.000007880059,0.00003064626,0.000006111112,0.9374064,0.002802035,0.05872956,0.0007724233,0.000009798534],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02227971,0.00006244262,0.97563,0.0001239026,0.00002831768,0.00004665782,0.00002130143,0.0003943444,0.001413369],"genre_scores_gemma":[0.8484276,0.0001531558,0.1480691,0.0001275688,0.00003715374,0.0001773945,0.0000858792,0.00007964038,0.002842513],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001632248,"threshold_uncertainty_score":0.005553186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01414252212207897,"score_gpt":0.2760133025861901,"score_spread":0.2618707804641111,"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."}}