{"id":"W3200155431","doi":"10.48550/arxiv.2109.05110","title":"An Empirical Comparison of Off-policy Prediction Learning Algorithms in the Four Rooms Environment","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Algorithm; Artificial intelligence; Machine learning","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":[0.009938755,0.001551624,0.001466056,0.001840757,0.0007522907,0.001311898,0.002223736,0.002690628,0.001365278],"category_scores_gemma":[0.0355777,0.0004267539,0.0008915319,0.001496302,0.001238302,0.003256566,0.001456667,0.002976537,0.0005740536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001909296,"about_ca_system_score_gemma":0.001844664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008384654,"about_ca_topic_score_gemma":0.005338987,"domain_scores_codex":[0.9957628,0.001784929,0.0003569219,0.0008552187,0.0008169606,0.000423255],"domain_scores_gemma":[0.9648861,0.02759238,0.001175244,0.002586,0.002767805,0.0009924851],"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":[0.003178186,0.002173779,0.02815629,0.0004970259,0.0002889599,0.0001269715,0.0001811153,0.6637493,0.001543012,0.00401428,0.007912196,0.2881789],"study_design_scores_gemma":[0.0001508483,0.0009026962,0.004488585,0.00004934329,0.00004720211,0.00006584072,0.0001290714,0.9885356,0.002122218,0.002403807,0.001076118,0.00002877872],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8961235,0.005333283,0.0853029,0.001325799,0.0004443497,0.0003670125,0.0007156046,0.002259366,0.008128102],"genre_scores_gemma":[0.9315037,0.000852172,0.06338205,0.0003154611,0.00007616905,0.0002562899,0.001739963,0.0001515125,0.001722699],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.009938755,"threshold_uncertainty_score":0.05256182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1066680578552088,"score_gpt":0.250100170987369,"score_spread":0.1434321131321602,"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."}}