{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001231297,0.0004995131,0.0004986183,0.00021385,0.0003410152,0.0006276862,0.001415943,0.0007629989,0.009138077],"category_scores_gemma":[0.004190159,0.0002826594,0.0005435396,0.000161218,0.001160444,0.001045061,0.001606107,0.001383104,0.0007659168],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006858534,"about_ca_system_score_gemma":0.001234799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003858507,"about_ca_topic_score_gemma":0.004591865,"domain_scores_codex":[0.9995264,0.0001507369,0.00002379836,0.00009524592,0.0001136469,0.00009010525],"domain_scores_gemma":[0.9986726,0.0008368267,0.00009559727,0.0001658173,0.0001239806,0.0001052977],"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":[0.0004964662,0.0005175594,0.004018009,0.0002382448,0.00007475574,0.0002527252,0.0002478987,0.7808319,0.00775547,0.06729143,0.007868478,0.1304071],"study_design_scores_gemma":[0.00002805509,0.00003289665,0.0001230695,0.000004948217,0.000003060136,0.00001136638,0.000006436433,0.9862171,0.002090062,0.01074827,0.0007300874,0.000004539259],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08397824,0.00004489669,0.8986171,0.0005544662,0.00008374641,0.0001521995,0.0001400315,0.005161967,0.01126731],"genre_scores_gemma":[0.7548553,0.00003053054,0.2388297,0.0002443574,0.0000181026,0.0001986983,0.0002003675,0.000342552,0.005280323],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009138077,"threshold_uncertainty_score":0.03056991,"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."}}