{"id":"W3158744994","doi":"","title":"Adaptive Approximate Policy Iteration","year":2021,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Regret; Reinforcement learning; Markov decision process; Computer science; Ergodic theory; Tilde; Q-learning; Bellman equation; Mathematical optimization; Novelty; Function (biology); Upper and lower bounds; Function approximation; Scheme (mathematics); Adaptive learning; Online learning; Markov process; Artificial intelligence; Mathematics; Machine learning; Discrete mathematics; Statistics","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":[0.0001653913,0.0001395545,0.0001212239,0.000141355,0.0001272911,0.0006415708,0.0003889259,0.00005241369,0.0001673895],"category_scores_gemma":[0.0005157425,0.000143072,0.00002486058,0.0002045296,0.00008975077,0.0003015184,0.0001634592,0.0001674453,0.0001424571],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005983996,"about_ca_system_score_gemma":0.0002217772,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002305007,"about_ca_topic_score_gemma":0.00001693015,"domain_scores_codex":[0.9986472,0.00007656644,0.000335116,0.0003460521,0.0003995312,0.0001955633],"domain_scores_gemma":[0.9987803,0.0002063275,0.0001163394,0.0002339948,0.0005796042,0.0000834514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001415706,0.00003050618,0.00001054938,0.000003163938,0.00001597529,0.00003319847,0.000436227,0.01471246,0.0005218173,0.877187,0.00007788377,0.1069571],"study_design_scores_gemma":[0.00001994451,0.00009212596,0.00004911273,0.00002468185,0.000002532074,0.00001633607,0.0002088375,0.7741322,0.004182708,0.2208866,0.0002599831,0.0001249109],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00008508697,0.000008749351,0.9813523,0.00285892,0.0004974633,0.00007111095,0.0000350694,0.00005395017,0.01503739],"genre_scores_gemma":[0.8424873,0.0001598415,0.1553076,0.0007249446,0.0001528442,0.000009368199,0.00005388448,0.000007843561,0.001096389],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8424022,"threshold_uncertainty_score":0.6186682,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1202154481482684,"score_gpt":0.3511960815700123,"score_spread":0.2309806334217439,"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."}}