{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.001843314,0.0002469934,0.0002692733,0.0009085173,0.001358004,0.003815184,0.01027968,0.0001307287,0.000002551458],"category_scores_gemma":[0.0003791106,0.0002580405,0.00005878957,0.0005801287,0.0008272598,0.007079501,0.02043704,0.001261701,0.00006198742],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001710074,"about_ca_system_score_gemma":0.0003577308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003911544,"about_ca_topic_score_gemma":0.000004219778,"domain_scores_codex":[0.9976854,0.0001508887,0.0007303031,0.000400761,0.0006471953,0.0003854941],"domain_scores_gemma":[0.9938077,0.0002036832,0.0007409982,0.004723398,0.0003798337,0.0001443893],"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":[0.000001266403,0.00001999305,0.001472052,0.00006117141,0.000006168578,0.000001013941,0.005624697,0.6659276,0.000003861884,0.03974219,0.0000641004,0.2870758],"study_design_scores_gemma":[0.0001748321,0.00003554201,0.01377676,0.00012993,0.00000301783,0.0000119966,0.00002597636,0.9608265,0.000008117184,0.0007671694,0.02398334,0.0002568554],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0008219673,0.0002029439,0.9816179,0.001535413,0.0008663356,0.0003650397,9.770782e-7,0.0001830757,0.01440634],"genre_scores_gemma":[0.7364022,0.002363465,0.2604456,0.0006339923,0.00003457424,0.00005068153,0.00002832617,0.000006525275,0.00003461298],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7355802,"threshold_uncertainty_score":0.9999872,"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."}}