{"id":"W3105108801","doi":"","title":"The LoCA Regret: A Consistent Metric to Evaluate Model-Based Behavior in Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Energy, Environment, and Transportation Policies","field":"Energy","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Reinforcement learning; Regret; Metric (unit); Computer science; Artificial intelligence; Machine learning; Task (project management); Representation (politics); Adaptation (eye); Sample (material); Variation (astronomy)","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":[0.01278949,0.002381153,0.001768221,0.001492597,0.0007362058,0.001990076,0.002192726,0.002777535,0.001948213],"category_scores_gemma":[0.06403121,0.0004899729,0.0009156735,0.0009922005,0.002812466,0.002949194,0.002536613,0.004063218,0.0005715137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002568744,"about_ca_system_score_gemma":0.00248727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003874222,"about_ca_topic_score_gemma":0.004141708,"domain_scores_codex":[0.9912539,0.004548319,0.0005326563,0.001261149,0.001946492,0.0004575536],"domain_scores_gemma":[0.9617853,0.02629708,0.003735543,0.004015164,0.002652433,0.001514481],"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":[0.000997788,0.0005929021,0.01234908,0.0004942906,0.0004601086,0.00009890281,0.0001185889,0.8954917,0.003855184,0.01274389,0.008103636,0.0646939],"study_design_scores_gemma":[0.00006721263,0.0007420225,0.002183957,0.000055274,0.00003994567,0.00005533207,0.00003612978,0.9804007,0.002573637,0.01279324,0.001006217,0.00004644069],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1952763,0.003799664,0.783113,0.002476824,0.000641362,0.0004776395,0.001917936,0.003704874,0.008592405],"genre_scores_gemma":[0.8375233,0.0005279329,0.1557361,0.0008021339,0.0001357975,0.0007302364,0.001992629,0.000673697,0.00187807],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01278949,"threshold_uncertainty_score":0.0676381,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01964811261471099,"score_gpt":0.2450699688904024,"score_spread":0.2254218562756914,"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."}}