{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00465734,0.00126134,0.001488239,0.00159061,0.0004923088,0.002857871,0.001775841,0.00177432,0.003183232],"category_scores_gemma":[0.03045781,0.0007237415,0.0009662239,0.002336159,0.002735879,0.004878273,0.001278157,0.002495033,0.0007883376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00167465,"about_ca_system_score_gemma":0.001287367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002041447,"about_ca_topic_score_gemma":0.001245012,"domain_scores_codex":[0.9970482,0.001200976,0.0001832415,0.0007356035,0.0006543045,0.000177672],"domain_scores_gemma":[0.9565618,0.03671146,0.002077174,0.00220142,0.001901364,0.0005467433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0004505029,0.0007826675,0.03729085,0.004972302,0.0004976688,0.0001393093,0.0006202097,0.1661675,0.002115426,0.1190038,0.005251082,0.6627086],"study_design_scores_gemma":[0.0001298481,0.001350866,0.04250812,0.002115165,0.0004883515,0.0008159594,0.001278499,0.6285122,0.005069979,0.2518295,0.06558669,0.0003148854],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1751858,0.2498701,0.5246993,0.00776251,0.0003454538,0.000286406,0.0007028383,0.001246874,0.03990075],"genre_scores_gemma":[0.8548281,0.08804004,0.05250425,0.0007324736,0.0005319727,0.0002182049,0.0003907674,0.0002766857,0.002477545],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00465734,"threshold_uncertainty_score":0.02463067,"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."}}