{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001030385,0.0008060034,0.0005927049,0.0002459231,0.0003958509,0.0006754923,0.001307733,0.0008513989,0.003849208],"category_scores_gemma":[0.004323387,0.0003365954,0.0004052014,0.0002297791,0.0009460435,0.001546238,0.001150979,0.001791632,0.0005722059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000849223,"about_ca_system_score_gemma":0.001461535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00260753,"about_ca_topic_score_gemma":0.00375422,"domain_scores_codex":[0.999495,0.0001812288,0.00003467238,0.0001102279,0.0001242502,0.00005456463],"domain_scores_gemma":[0.9982952,0.001081836,0.0001757521,0.0001813674,0.0001559223,0.0001098965],"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":[0.0002160256,0.0001634523,0.0008266177,0.000116409,0.00002674017,0.0001536934,0.0002090677,0.8532411,0.006807208,0.02797533,0.001420879,0.1088436],"study_design_scores_gemma":[0.00002843099,0.0000402218,0.00003322943,0.00000703686,0.000004605381,0.00001386336,0.00001252733,0.9883752,0.001907351,0.008885316,0.0006880828,0.00000409815],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0151897,0.00004500354,0.981121,0.000197426,0.00002084342,0.00006565416,0.00002401425,0.001072084,0.002264343],"genre_scores_gemma":[0.6399556,0.0001042703,0.3561103,0.000191522,0.00002402274,0.0002162335,0.00008730694,0.0001583802,0.003152387],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003849208,"threshold_uncertainty_score":0.01287687,"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."}}