{"id":"W3037660226","doi":"10.65109/yiph3635","title":"Maximizing Information Gain in Partially Observable Environments via Prediction Rewards","year":2020,"lang":"en","type":"article","venue":"","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"European Commission","keywords":"MNIST database; Computer science; Reinforcement learning; Artificial intelligence; Action selection; Inference; Entropy (arrow of time); Function (biology); Realizability; Machine learning; Deep learning; Perception; Algorithm","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":[0.002170724,0.001215337,0.001255007,0.0005408334,0.0005035885,0.001604205,0.001417998,0.00158061,0.001778159],"category_scores_gemma":[0.01362863,0.0007737362,0.0004570545,0.0004981302,0.001983612,0.003723654,0.002436192,0.002230364,0.000279002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00179268,"about_ca_system_score_gemma":0.001354502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003052767,"about_ca_topic_score_gemma":0.003533377,"domain_scores_codex":[0.9988865,0.0004331737,0.00005024287,0.000259951,0.0002197545,0.0001504548],"domain_scores_gemma":[0.9916849,0.006891664,0.0004823004,0.0003533027,0.0003404493,0.0002473792],"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":[0.0001393914,0.00007910038,0.001066666,0.0001063688,0.00005276004,0.0001092225,0.0001410597,0.9038435,0.001921204,0.0608145,0.001190403,0.03053589],"study_design_scores_gemma":[0.000009901646,0.00002719051,0.0001503818,0.000009461787,0.000006057287,0.00001290294,0.000008430284,0.9526805,0.0004528994,0.04644094,0.0001937414,0.000007519153],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06806193,0.0005912221,0.9247776,0.001419008,0.00005185226,0.00005175869,0.0001130583,0.00042958,0.004503841],"genre_scores_gemma":[0.9368631,0.000371815,0.05957371,0.0002285253,0.00006270007,0.00009709,0.00009755611,0.00009037829,0.002615147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003052767,"threshold_uncertainty_score":0.01300687,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02620721636987957,"score_gpt":0.2058696704913703,"score_spread":0.1796624541214907,"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."}}