{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001525364,0.0001866415,0.000205888,0.0002227433,0.0001887255,0.0002795904,0.0007389823,0.00004907088,0.0003145221],"category_scores_gemma":[0.0007991072,0.0001756447,0.00007086123,0.0003477122,0.0001561734,0.001181583,0.0001988193,0.0004815327,0.0001254831],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000481561,"about_ca_system_score_gemma":0.0002001652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002726371,"about_ca_topic_score_gemma":0.000001273728,"domain_scores_codex":[0.9980873,0.0001288065,0.0004905353,0.0002948297,0.0007886778,0.0002098133],"domain_scores_gemma":[0.9980388,0.0003272547,0.000540937,0.0002056575,0.0007667891,0.0001205277],"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":[0.00004243339,0.00001205305,0.003023672,0.00001174607,0.00007806011,0.000003993664,0.005840524,0.642129,0.00050258,0.3469694,0.00003193253,0.001354612],"study_design_scores_gemma":[0.0009839728,0.0008597904,0.003833747,0.0001541729,0.00001456706,0.000009849221,0.004964504,0.9822478,0.002497911,0.000198552,0.003961774,0.0002733667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003317977,0.000002275644,0.820886,0.004574232,0.00009730372,0.0002202034,0.000002427266,0.0001884749,0.1707112],"genre_scores_gemma":[0.9880551,0.0000277035,0.01056406,0.0003589468,0.00004024322,0.00002729353,0.0001018807,0.000009455542,0.0008152847],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9847372,"threshold_uncertainty_score":0.7162581,"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."}}