{"id":"W3204811657","doi":"","title":"LOCO: Adaptive exploration in reinforcement learning via local estimation of contraction coefficients","year":2021,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Reinforcement learning; Contraction (grammar); Computer science; Reinforcement; Artificial intelligence; Control theory (sociology); Mathematics; Mathematical optimization; Engineering; Structural engineering","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":[0.0003566926,0.0001686871,0.0002008053,0.0003809618,0.0001554432,0.0001841462,0.0004058494,0.00008667698,0.0002022287],"category_scores_gemma":[0.0006276535,0.0001961583,0.00006454011,0.0005529226,0.0000805369,0.001120142,0.0001617019,0.0005508849,0.00009713359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002415734,"about_ca_system_score_gemma":0.0002002827,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001452167,"about_ca_topic_score_gemma":0.00002408309,"domain_scores_codex":[0.997557,0.0002883665,0.0006368143,0.000453548,0.0008396455,0.0002245878],"domain_scores_gemma":[0.9980517,0.0003179026,0.0004827532,0.0002908312,0.0007933188,0.00006348991],"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":[0.00003415384,0.00007615142,0.0009881787,0.000006294771,0.00003230035,0.00001553201,0.001579817,0.9130818,0.001554049,0.05724219,0.00001599608,0.02537356],"study_design_scores_gemma":[0.0006808459,0.0002245279,0.00237476,0.0001308324,0.000007318637,0.000009811341,0.00149873,0.9890459,0.004594549,0.001087324,0.0001816313,0.0001637273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00653691,0.000007121698,0.9782869,0.0009050752,0.0004522514,0.0002120989,6.589449e-7,0.00009987496,0.01349906],"genre_scores_gemma":[0.9919596,0.00004024869,0.005850109,0.0000535147,0.00002895733,0.00004986242,0.0001588193,0.00001236532,0.001846485],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9854227,"threshold_uncertainty_score":0.7999102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05327394860873119,"score_gpt":0.3325311095023211,"score_spread":0.2792571608935899,"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."}}