{"id":"W3111378514","doi":"10.1613/jair.1.12087","title":"Adapting Behavior via Intrinsic Reward: A Survey and Empirical Study","year":2020,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Alberta Machine Intelligence Institute; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Computer science; Active learning (machine learning); Artificial intelligence; Introspection; Proactive learning; Representation (politics); Testbed; Machine learning; Cognitive psychology; Robot learning; Psychology","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0084314,0.0001257143,0.0003044984,0.0003089241,0.000285184,0.0004403908,0.001041856,0.00005909339,0.0000300236],"category_scores_gemma":[0.002689013,0.0001016436,0.00006973888,0.001340998,0.0001305509,0.0003570342,0.0005486701,0.001476998,0.00005507907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000443201,"about_ca_system_score_gemma":0.0002328453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002445739,"about_ca_topic_score_gemma":0.00006116438,"domain_scores_codex":[0.9956856,0.001572674,0.0007236287,0.0003441502,0.001248893,0.0004250802],"domain_scores_gemma":[0.997274,0.0009929162,0.0001946391,0.0002379103,0.0008752011,0.0004252786],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001300895,0.0005349406,0.08357313,0.00001136553,0.00003049358,0.0005404793,0.007847617,0.0002353033,0.0007281273,0.0002611848,0.000236397,0.9058709],"study_design_scores_gemma":[0.0004863528,0.02216074,0.3064917,0.0001488198,0.00005130905,0.0007493237,0.01273302,0.6394618,0.007477134,0.007242729,0.001929741,0.001067303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7148517,0.0001451071,0.2814116,0.003133372,0.0001958699,0.0002008333,7.117567e-7,0.00002421269,0.00003661983],"genre_scores_gemma":[0.9929092,0.00002464017,0.006516035,0.00008005897,0.0004404161,0.000003492969,2.078553e-7,0.00001043957,0.00001552236],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9048036,"threshold_uncertainty_score":0.6416904,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3247034389713216,"score_gpt":0.4767867490410224,"score_spread":0.1520833100697008,"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."}}