{"id":"W2995040055","doi":"","title":"Reinforcement Learning with Competitive Ensembles of Information-Constrained Primitives","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Context (archaeology); Generalization; Artificial intelligence; Decomposition; State (computer science); Machine learning; Mathematics","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":[0.002080761,0.0007965983,0.001149424,0.000374803,0.0004258653,0.0009927446,0.001670972,0.00100905,0.002191281],"category_scores_gemma":[0.006785824,0.0004788376,0.0005067021,0.0003340623,0.001462568,0.001696157,0.00163521,0.001553625,0.0003118448],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001382437,"about_ca_system_score_gemma":0.001459161,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004258293,"about_ca_topic_score_gemma":0.003978863,"domain_scores_codex":[0.9988752,0.0003721208,0.00006275684,0.0002356628,0.0002723764,0.0001819181],"domain_scores_gemma":[0.9969845,0.001455346,0.0003934198,0.0004373956,0.0003612055,0.0003681829],"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":[0.0002035694,0.0001322902,0.0009853044,0.00004165158,0.00004937849,0.00006647327,0.00008453937,0.9475821,0.00281169,0.02088561,0.0005588253,0.0265986],"study_design_scores_gemma":[0.00001801032,0.00003935879,0.00007648888,0.000002341392,0.000004580063,0.000006184674,0.000004636787,0.9928604,0.0003468688,0.006516262,0.0001206621,0.000004331596],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2262359,0.0002340944,0.7651577,0.0006098082,0.00007493919,0.0001411488,0.00007087168,0.0008173859,0.006658184],"genre_scores_gemma":[0.9661897,0.00004267916,0.0321318,0.00009137716,0.00001576966,0.0000784876,0.00004150745,0.00002352323,0.001384983],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004258293,"threshold_uncertainty_score":0.01100421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03585979767524092,"score_gpt":0.2877329669438369,"score_spread":0.251873169268596,"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."}}