{"id":"W2342981176","doi":"10.1007/978-3-319-57969-6_1","title":"NeuroHex: A Deep Q-learning Hex Agent","year":2017,"lang":"en","type":"preprint","venue":"Communications in computer and information science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Olympiad; Reinforcement learning; Computer science; Q-learning; Champion; Artificial intelligence; Initialization; State (computer science); Convolutional neural network; Action (physics); Algorithm; Mathematics; Political science; Law; Mathematics education","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":[0.0005839162,0.0004242116,0.0006685969,0.0002419577,0.0004641986,0.000754245,0.001426909,0.001080239,0.01267786],"category_scores_gemma":[0.001716593,0.0003249912,0.0003115637,0.0002561402,0.0006508059,0.0009462251,0.001873384,0.001166748,0.001860716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005773949,"about_ca_system_score_gemma":0.001392958,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003770662,"about_ca_topic_score_gemma":0.00435163,"domain_scores_codex":[0.999821,0.00004640163,0.000009532921,0.00003641189,0.00005304056,0.00003364246],"domain_scores_gemma":[0.9996651,0.0001118343,0.00002135731,0.00005601252,0.00007866652,0.00006708988],"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":[0.0009398321,0.0004004338,0.00213905,0.0002278914,0.0001240008,0.0002751809,0.0001274829,0.568047,0.006930191,0.06476507,0.02306118,0.3329627],"study_design_scores_gemma":[0.0000854387,0.00008090377,0.000070833,0.00001046195,0.00001024821,0.0000230205,0.000013074,0.9813429,0.001703562,0.01209192,0.004560417,0.000007269135],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02915014,0.0002982219,0.9482116,0.0008462164,0.000371408,0.0002281487,0.0004093795,0.00593418,0.01455074],"genre_scores_gemma":[0.5569311,0.0002411256,0.4167782,0.0007570624,0.00008526762,0.0003647776,0.0004670772,0.0003883489,0.023987],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01267786,"threshold_uncertainty_score":0.04241163,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05352251106668458,"score_gpt":0.326837449672273,"score_spread":0.2733149386055884,"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."}}