{"id":"W2964295739","doi":"","title":"Imagination-Augmented Agents for Deep Reinforcement Learning","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":163,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Reinforcement learning; Robustness (evolution); Computer science; Artificial intelligence; Construct (python library); Policy learning; Machine learning; Contrast (vision); Deep learning; Context (archaeology); Architecture","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":[0.0002569809,0.0001626348,0.0001428837,0.0001286689,0.001086613,0.0003607844,0.001712076,0.0000586294,0.00004311657],"category_scores_gemma":[0.0002108184,0.000190562,0.0001080869,0.0001424806,0.00008996658,0.001305494,0.0005407777,0.0001577804,0.000121041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001535904,"about_ca_system_score_gemma":0.00004477881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002914325,"about_ca_topic_score_gemma":0.000004092922,"domain_scores_codex":[0.9988506,0.00003764438,0.0001593805,0.0004698528,0.0001155496,0.0003669108],"domain_scores_gemma":[0.9983019,0.00007673725,0.0003472595,0.0009628466,0.0001930266,0.0001182889],"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":[0.00001083843,0.00001176179,0.004639879,0.00001196691,0.00003420143,0.00001949459,0.00011821,0.8581836,0.00003057792,0.1360206,0.0001987558,0.0007201487],"study_design_scores_gemma":[0.001031455,0.0001106828,0.002542647,0.00001765658,0.00002170997,0.000001309802,0.00004501782,0.9879441,0.0001831261,0.001090755,0.006795222,0.0002163043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006112494,0.000005699126,0.9831771,0.0001910183,0.0003516741,0.0002896061,2.392711e-7,0.0001624218,0.009709782],"genre_scores_gemma":[0.9774202,0.00002840825,0.003015302,0.0001024224,0.00003797056,0.000001696441,0.000009398245,0.00001239997,0.01937227],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9801618,"threshold_uncertainty_score":0.8357456,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0722518834787979,"score_gpt":0.2207498508139353,"score_spread":0.1484979673351374,"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."}}