{"id":"W1529722424","doi":"10.1007/11944836_23","title":"Testing Probabilistic Equivalence Through Reinforcement Learning","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université Laval","funders":"","keywords":"Equivalence (formal languages); Markov decision process; Probabilistic logic; Computer science; Reinforcement learning; Bisimulation; TRACE (psycholinguistics); Markov process; Witness; Theoretical computer science; Algorithm; Artificial intelligence; Discrete mathematics; Mathematics; Programming language; Statistics","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":[0.006124888,0.001182703,0.001445926,0.0009211593,0.0006204235,0.00129145,0.003426525,0.001818997,0.006181356],"category_scores_gemma":[0.05523177,0.0007624647,0.001546012,0.0005733062,0.003697338,0.005974245,0.004803332,0.003666529,0.0006680459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001535684,"about_ca_system_score_gemma":0.002160528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002221232,"about_ca_topic_score_gemma":0.002313205,"domain_scores_codex":[0.9895179,0.00424319,0.0004359624,0.002112841,0.002799387,0.00089069],"domain_scores_gemma":[0.9341697,0.05708485,0.001837863,0.004113116,0.001912328,0.0008821983],"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":[0.001607625,0.001201337,0.007093688,0.0003191602,0.0002045617,0.0003085499,0.0002879278,0.5622704,0.007787289,0.1328427,0.003568049,0.2825086],"study_design_scores_gemma":[0.00009856428,0.0001388587,0.000337118,0.00001704802,0.00001787358,0.00004035272,0.00002713562,0.8577433,0.00307408,0.1381423,0.0003493121,0.00001426789],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.106034,0.0001113271,0.8843655,0.0007512447,0.0001247512,0.0001755623,0.0001091183,0.001994377,0.006334144],"genre_scores_gemma":[0.860729,0.0000494473,0.136184,0.0002174325,0.00005935793,0.0001611765,0.0002892412,0.0002316356,0.002078759],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006181356,"threshold_uncertainty_score":0.03239185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05150164505242391,"score_gpt":0.2925115154425397,"score_spread":0.2410098703901158,"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."}}