{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001545106,0.00118908,0.001229446,0.0005919543,0.0004008342,0.0009562206,0.002276749,0.001547879,0.006116525],"category_scores_gemma":[0.005131155,0.0007054752,0.0008152984,0.0005514525,0.0017138,0.001862533,0.002263115,0.002978937,0.001110682],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001651449,"about_ca_system_score_gemma":0.001461511,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003767609,"about_ca_topic_score_gemma":0.00528823,"domain_scores_codex":[0.9993774,0.0002165155,0.00003144854,0.0001495697,0.0001540755,0.00007103664],"domain_scores_gemma":[0.9981426,0.001219272,0.0001403741,0.0002075724,0.0002023664,0.0000877467],"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":[0.000096374,0.0001028832,0.0003969334,0.000141795,0.00006794993,0.00005755951,0.00007482952,0.8258486,0.00150909,0.08335168,0.004242995,0.0841093],"study_design_scores_gemma":[0.00001241391,0.0000136638,0.0000268523,0.000008022828,0.000003797835,0.000006457643,0.000003405448,0.9709445,0.0003231056,0.02804361,0.0006105845,0.000003614759],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002686102,0.0002097233,0.994508,0.0001859065,0.00003051739,0.0000366953,0.00003984449,0.0003810233,0.001922136],"genre_scores_gemma":[0.4288306,0.0005703701,0.5535725,0.0005532909,0.0001448959,0.000613758,0.0003916706,0.0006602788,0.01466259],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.006116525,"threshold_uncertainty_score":0.02046186,"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."}}