{"id":"W3177370677","doi":"10.1609/aaai.v35i18.17927","title":"Solving JumpIN’ Using Zero-Dependency Reinforcement Learning (Student Abstract)","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Reinforcement learning; Computer science; Dependency grammar; Python (programming language); Interpretability; Dependency (UML); GRASP; Modular design; Backtracking; Artificial intelligence; Algorithm; Programming language","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"],"consensus_categories":[],"category_scores_codex":[0.0007430429,0.0003415863,0.0003660634,0.0001604236,0.0005145564,0.0007255455,0.002342921,0.0001352267,0.0002144483],"category_scores_gemma":[0.0007625604,0.0002957761,0.0002098584,0.00082428,0.0001793491,0.0007608246,0.001268049,0.000777412,0.00013241],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001676819,"about_ca_system_score_gemma":0.000309836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004215307,"about_ca_topic_score_gemma":0.000003149584,"domain_scores_codex":[0.9964437,0.00002858944,0.0009917694,0.0006930002,0.001222818,0.0006200916],"domain_scores_gemma":[0.9972293,0.0001267824,0.0008073674,0.0004971907,0.001201741,0.0001375632],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001831229,0.0001022205,0.0009582368,0.00008521319,0.00004984361,0.000006326128,0.002353576,0.3655541,0.1051123,0.5135895,0.0000470513,0.01212329],"study_design_scores_gemma":[0.00004551401,0.0001461011,0.0003351865,0.0004746362,0.00002428827,0.00001709287,0.0009487725,0.5688918,0.4147283,0.01387592,0.0001477739,0.0003645987],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1053666,0.00006145634,0.8494557,0.001326227,0.001280114,0.0005211752,6.008367e-7,0.0002378777,0.04175021],"genre_scores_gemma":[0.9903032,0.00007767408,0.007880482,0.0001856627,0.00007822754,0.00001108244,8.420997e-7,0.00002322829,0.001439629],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8849365,"threshold_uncertainty_score":0.9999495,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08900379891208272,"score_gpt":0.3197357785665688,"score_spread":0.2307319796544861,"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."}}