{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000637539,0.001006778,0.0006190591,0.0002275937,0.0002907305,0.0007924768,0.001436968,0.0009162329,0.004467667],"category_scores_gemma":[0.002716118,0.0004008099,0.0005140908,0.0002461357,0.00103807,0.001286153,0.001522767,0.002684949,0.0006475075],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008602045,"about_ca_system_score_gemma":0.001016545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002402872,"about_ca_topic_score_gemma":0.003583369,"domain_scores_codex":[0.9997209,0.0001004831,0.00001607565,0.00006408172,0.00006884366,0.00002956691],"domain_scores_gemma":[0.9993116,0.0003604277,0.0000783715,0.0001104065,0.00007455381,0.0000645862],"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":[0.0001168091,0.000102459,0.0006961056,0.000158297,0.00007477199,0.0001000536,0.00009857475,0.7695029,0.003570453,0.1325376,0.003398571,0.08964347],"study_design_scores_gemma":[0.00001066638,0.00002529468,0.00002964965,0.000009672192,0.000005551562,0.000009865706,0.000003142516,0.9611621,0.0006922683,0.0364928,0.001553781,0.000005235242],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005795544,0.0003030326,0.9899272,0.0002455791,0.00007256204,0.00002910322,0.00006015157,0.0006514946,0.002915336],"genre_scores_gemma":[0.630657,0.0005337938,0.3615981,0.0002821274,0.00009173816,0.0003114367,0.0002295709,0.0002038614,0.00609235],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004467667,"threshold_uncertainty_score":0.01494581,"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."}}