{"id":"W2995372087","doi":"","title":"Learning the Arrow of Time for Problems in Reinforcement Learning","year":2020,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Arrow; Arrow of time; Computer science; Reinforcement learning; Markov decision process; Reachability; Artificial intelligence; Machine learning; Class (philosophy); Function (biology); Markov process; Selection (genetic algorithm); Process (computing); Theoretical computer science; Mathematics","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":[],"consensus_categories":[],"category_scores_codex":[0.0005441699,0.0001839488,0.0002199406,0.0001966911,0.0002517054,0.0002440646,0.001162859,0.000065185,0.0002247611],"category_scores_gemma":[0.002136931,0.0001630901,0.0001039366,0.0004311133,0.00008864843,0.0004090534,0.0002710261,0.0007991255,0.0001207361],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007002158,"about_ca_system_score_gemma":0.0001230649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004974317,"about_ca_topic_score_gemma":0.000002902915,"domain_scores_codex":[0.9977693,0.0002372691,0.0005993201,0.0004495223,0.0006563553,0.0002882312],"domain_scores_gemma":[0.9980472,0.0007191609,0.0004989118,0.0002456129,0.0004087607,0.00008036873],"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":[0.00002243277,0.00001735856,0.006602733,0.00001668122,0.00004274648,0.000001583866,0.006137292,0.9505544,0.003073388,0.03184057,0.0001270384,0.001563802],"study_design_scores_gemma":[0.0005921012,0.0005697722,0.001260863,0.00008935545,0.000007452999,0.000002132561,0.0007124101,0.9905544,0.0005023136,0.000438917,0.005105117,0.0001651878],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007360958,0.00001102135,0.9454944,0.01317117,0.0002168591,0.0007088621,0.000001067367,0.0002037459,0.03283199],"genre_scores_gemma":[0.990382,0.000040954,0.002130624,0.0002251217,0.00008191261,0.0001214853,0.00005675653,0.00001920282,0.006941912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9830211,"threshold_uncertainty_score":0.6650621,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05955057235187068,"score_gpt":0.3172682931974696,"score_spread":0.2577177208455989,"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."}}