{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005488487,0.0006940293,0.0006356091,0.0002133043,0.0002683781,0.0004742848,0.000853216,0.0006096628,0.001515901],"category_scores_gemma":[0.001527225,0.0003206166,0.0003066311,0.0001195491,0.0006312895,0.0006604081,0.0009114702,0.001064167,0.0001681915],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006159308,"about_ca_system_score_gemma":0.0008133739,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006051309,"about_ca_topic_score_gemma":0.004910793,"domain_scores_codex":[0.999837,0.00004370501,0.000007968236,0.00003602919,0.00003588609,0.0000392919],"domain_scores_gemma":[0.9996141,0.0001760504,0.00006403229,0.00002736302,0.00006214336,0.00005645653],"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":[0.00006683307,0.00006470879,0.0009112631,0.00002815166,0.00001976837,0.00007038577,0.00004983754,0.9680113,0.001807924,0.00524928,0.0004617436,0.0232587],"study_design_scores_gemma":[0.000005099338,0.00001856431,0.00003985689,0.00000180769,0.000001912118,0.00000445315,0.000002661002,0.9984568,0.0001764325,0.001192576,0.0000981893,0.000001595199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1595964,0.0003376999,0.8315427,0.0004390914,0.00008054377,0.0001084975,0.00004302785,0.0009179963,0.006933987],"genre_scores_gemma":[0.9689401,0.00006286346,0.02874588,0.00008203657,0.000008137157,0.00006822261,0.00002338347,0.00002028751,0.002049043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006051309,"threshold_uncertainty_score":0.01203215,"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."}}