{"id":"W2808386811","doi":"10.65109/fknq6967","title":"Teaching Multiple Tasks to an RL Agent using LTL","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":89,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Reinforcement learning; Computer science; Linear temporal logic; Convergence (economics); Exploit; Temporal logic; State (computer science); Artificial intelligence; Model checking; Theoretical computer science; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003798645,0.0001132484,0.00009516683,0.0001017601,0.0002945421,0.0002539596,0.0008342366,0.00003780357,0.0000539886],"category_scores_gemma":[0.0001077833,0.0001019533,0.00002988139,0.0001676666,0.00002699039,0.0005361431,0.0004633337,0.0001324362,0.0003659634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006934304,"about_ca_system_score_gemma":0.00003288544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003859095,"about_ca_topic_score_gemma":0.00003154564,"domain_scores_codex":[0.9988278,0.00006897327,0.000183319,0.000323776,0.00027339,0.000322773],"domain_scores_gemma":[0.9989911,0.00004264539,0.00005199385,0.0006775443,0.0000634881,0.0001731689],"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":[0.000007539473,0.00007517299,0.006625351,0.00001162249,0.00002632555,0.00001397327,0.008774843,0.8856781,0.02336787,0.02546249,0.002009454,0.04794733],"study_design_scores_gemma":[0.0001140398,0.0001951402,0.0008547778,0.0000112387,0.000002281601,0.000005474866,0.00005653696,0.9823734,0.002007067,0.00004566129,0.01417396,0.0001604843],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08525823,0.000001392307,0.9059398,0.0002127032,0.0004735152,0.0001215266,1.271121e-7,0.0002479217,0.007744795],"genre_scores_gemma":[0.6047791,9.085344e-8,0.3926439,0.0009536582,0.0001529106,0.000001238584,5.681093e-7,0.000007572517,0.001460942],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5195209,"threshold_uncertainty_score":0.4703841,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05619774051327824,"score_gpt":0.3225648176939725,"score_spread":0.2663670771806943,"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."}}