{"id":"W2889665471","doi":"10.1109/agents.2018.8460004","title":"Autonomous Agents in Snake Game via Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Research (Canada)","funders":"People's Government of Jilin Province; National Research Foundation","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Constraint (computer-aided design); Dual (grammatical number); Machine learning; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004259529,0.000192876,0.000184283,0.0002284075,0.0001254385,0.0001916523,0.0009790758,0.00008232559,0.000657179],"category_scores_gemma":[0.00008502013,0.0001842573,0.00005561917,0.00049385,0.00007513904,0.0005047115,0.0005550223,0.0002834427,0.001768037],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001822957,"about_ca_system_score_gemma":0.00005640209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009182224,"about_ca_topic_score_gemma":0.0000287382,"domain_scores_codex":[0.9980689,0.0000724921,0.0004478257,0.0004168348,0.0004254408,0.0005684927],"domain_scores_gemma":[0.9989911,0.00005661693,0.0001466635,0.0005966951,0.00008819369,0.0001207765],"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":[0.000003995106,0.00001488007,0.003754335,0.000006804844,0.00001205225,0.00001549186,0.001390069,0.976404,0.0001045376,0.007755994,0.0002387216,0.01029916],"study_design_scores_gemma":[0.0004084398,0.0003069259,0.004063553,0.00001583276,0.000002464526,0.000007919975,0.00002621244,0.9767043,0.0006352914,0.0001499408,0.01744764,0.0002314705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003514752,0.000008160951,0.9235235,0.0002091147,0.0004264263,0.0001880318,1.043234e-8,0.0002987275,0.07183132],"genre_scores_gemma":[0.9631847,0.000006890511,0.02207488,0.000743078,0.00009061846,0.0000120083,0.000003118681,0.0000150282,0.01386967],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9596699,"threshold_uncertainty_score":0.9990092,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02487632976772243,"score_gpt":0.2714467120606008,"score_spread":0.2465703822928784,"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."}}