{"id":"W2785940258","doi":"","title":"An inference-based policy gradient method for learning options","year":2018,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Inference; Abstraction; Scalability; Artificial intelligence; Machine learning; A priori and a posteriori; Formalism (music); Differentiable function","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":[0.002442363,0.001063367,0.001430263,0.0009569292,0.0005461169,0.000980706,0.001784668,0.001751824,0.00395948],"category_scores_gemma":[0.007763845,0.000776151,0.0007514721,0.0007495132,0.001362277,0.001751147,0.001463595,0.00268233,0.0008276938],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001349533,"about_ca_system_score_gemma":0.002299175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004512019,"about_ca_topic_score_gemma":0.00472928,"domain_scores_codex":[0.9991097,0.0003966544,0.00004738124,0.000165791,0.0002075301,0.00007293632],"domain_scores_gemma":[0.9975803,0.0018733,0.0001285483,0.00009733492,0.0002338473,0.00008671219],"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":[0.0002211703,0.0001241752,0.0008085964,0.0001233544,0.00006486732,0.00009769679,0.00009563921,0.75534,0.001732495,0.03829569,0.002948912,0.2001474],"study_design_scores_gemma":[0.00001552864,0.00001869385,0.000030896,0.000007928235,0.000003506272,0.000008414873,0.000002984153,0.9919303,0.0002869536,0.007306059,0.0003839501,0.00000475993],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00421276,0.000180512,0.9940598,0.0001337283,0.00002723502,0.00005794075,0.00002844185,0.000480716,0.0008189812],"genre_scores_gemma":[0.2948868,0.0002573764,0.6998709,0.0003078292,0.00008071089,0.0004343138,0.0002169879,0.0002836851,0.003661426],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004512019,"threshold_uncertainty_score":0.01324576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02574182283153252,"score_gpt":0.2984720200177832,"score_spread":0.2727301971862506,"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."}}