{"id":"W3167763832","doi":"10.21428/594757db.8472938b","title":"General Deep Reinforcement Learning in NES Games","year":2021,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Acadia University","funders":"","keywords":"Reinforcement learning; Domain (mathematical analysis); Computer science; Video game; Artificial intelligence; Entertainment; Field (mathematics); Deep learning; Domain knowledge; Focus (optics); Hyperparameter; Human–computer interaction; Multimedia","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":[0.001184313,0.0005566982,0.0006470016,0.0002175569,0.0002322174,0.0006661167,0.0008158871,0.0008054352,0.002749402],"category_scores_gemma":[0.004034758,0.0003059772,0.0003426041,0.0001532719,0.0008002064,0.001036151,0.0009791212,0.001605124,0.0002970001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001217221,"about_ca_system_score_gemma":0.0009154729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006667321,"about_ca_topic_score_gemma":0.007567488,"domain_scores_codex":[0.99964,0.0001370247,0.00002025901,0.00007551147,0.00006086364,0.00006635644],"domain_scores_gemma":[0.9991944,0.0004274671,0.00008167998,0.00007627538,0.0001559858,0.00006410883],"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":[0.00005082207,0.00005021221,0.0007281777,0.00004046332,0.00001585129,0.00004382821,0.00003857688,0.9655002,0.0009723199,0.01505376,0.0007507195,0.01675517],"study_design_scores_gemma":[0.000005825669,0.0000139892,0.00007831751,0.000003614337,0.000001494668,0.000004693851,0.000003962817,0.9942842,0.0002054624,0.005140187,0.0002562487,0.00000192645],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1001955,0.0005432973,0.8866397,0.0007243,0.00007712998,0.00008917181,0.0001147538,0.0005831002,0.01103307],"genre_scores_gemma":[0.9304639,0.0001881678,0.06186591,0.0002027066,0.00002442236,0.00009961686,0.0001186328,0.00006088893,0.0069759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006667321,"threshold_uncertainty_score":0.01325703,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01572402921390724,"score_gpt":0.2488639597852059,"score_spread":0.2331399305712987,"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."}}