{"id":"W3171661360","doi":"","title":"Learning-Free Methods for Goal Conditioned Reinforcement Learning from Images","year":2021,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Machine Learning and ELM","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"University of Waterloo","keywords":"Reinforcement learning; Reinforcement; Psychology; Computer science; Artificial intelligence; Social psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004532763,0.0002964861,0.0005422476,0.0002523194,0.0006017935,0.000122224,0.001206595,0.0002913658,0.0003154547],"category_scores_gemma":[0.0002414937,0.0003627594,0.0003201459,0.000233791,0.00005089348,0.0003716498,0.0003273099,0.0005489154,0.00003050116],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007289059,"about_ca_system_score_gemma":0.0001376579,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01972619,"about_ca_topic_score_gemma":0.002356296,"domain_scores_codex":[0.9981003,0.0003855809,0.0001922595,0.0006592635,0.0003090745,0.0003535256],"domain_scores_gemma":[0.9981385,0.0003150914,0.0004965639,0.0005961102,0.000335431,0.0001182942],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0006490598,0.0002661906,0.0006707343,0.001343028,0.001546656,0.0001527677,0.5780542,0.05315832,0.03482629,0.005702565,0.01972252,0.3039077],"study_design_scores_gemma":[0.01116988,0.002951812,0.01229698,0.001661186,0.001246296,0.00001435486,0.4152722,0.4086368,0.03644875,0.006774033,0.09972386,0.003803831],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.3366804,0.0006467747,0.6528251,0.003035615,0.001599949,0.0007079793,0.00003066939,0.0006635239,0.003810051],"genre_scores_gemma":[0.0143746,0.0001128223,0.2149715,0.00002597396,0.00008132072,0.000002471293,0.002908169,0.00003269709,0.7674904],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7636803,"threshold_uncertainty_score":0.9998825,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01067963674525201,"score_gpt":0.2554117607650428,"score_spread":0.2447321240197908,"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."}}