{"id":"W3014454071","doi":"10.48550/arxiv.2004.00993","title":"Augmented Q Imitation Learning (AQIL)","year":2020,"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":"York University","funders":"","keywords":"Reinforcement learning; Imitation; Artificial intelligence; Q-learning; Computer science; Process (computing); Convergence (economics); Machine learning; Unsupervised learning; Reinforcement; Learning classifier system; Sequence learning; Psychology; Social psychology","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001969226,0.0003086079,0.0002887599,0.0002174722,0.0002043667,0.0002307407,0.001771382,0.0002395994,0.00003750116],"category_scores_gemma":[0.0001497943,0.0003927353,0.0001879149,0.0006392816,0.00006633316,0.0004242076,0.002460243,0.001137567,0.000406918],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000251096,"about_ca_system_score_gemma":0.0001737752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003947306,"about_ca_topic_score_gemma":0.000002410148,"domain_scores_codex":[0.9980209,0.0002101078,0.0002366382,0.001024062,0.000161752,0.000346496],"domain_scores_gemma":[0.9983465,0.0001222673,0.0003953777,0.0007893465,0.0001604368,0.0001860718],"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":[0.000009965558,0.00001245086,0.001301331,0.00005355648,0.00006758604,0.0001307758,0.0003691571,0.9286725,0.00005458408,0.06874577,0.0002819053,0.000300412],"study_design_scores_gemma":[0.0003414764,0.00008572414,0.0008257757,0.00006725146,0.00004638462,0.000001603281,0.00008472204,0.9917948,0.00007661532,0.004518883,0.001772352,0.0003843866],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01320135,0.0000171823,0.9781753,0.000340983,0.0006232806,0.000246362,0.000001178117,0.0006866609,0.006707723],"genre_scores_gemma":[0.9897085,0.00008359762,0.005954547,0.0001557525,0.0000748859,7.339598e-7,0.00004434255,0.00002380916,0.003953801],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9765072,"threshold_uncertainty_score":0.9998525,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1046833920474487,"score_gpt":0.1914710324459511,"score_spread":0.08678764039850238,"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."}}