{"id":"W3161449188","doi":"10.1109/smc52423.2021.9658917","title":"Feature-Based Interpretable Reinforcement Learning based on State-Transition Models","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Feature (linguistics); Transition (genetics); Artificial intelligence; State (computer science); Machine learning; Pattern recognition (psychology); Algorithm","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004687728,0.0003299246,0.0003237665,0.0002590826,0.0001915947,0.001071816,0.0006673522,0.0001356765,0.0001446023],"category_scores_gemma":[0.00006408638,0.0003381363,0.0001040912,0.0002664927,0.00006209197,0.0004538524,0.0000866976,0.0004376066,0.0001546199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002134937,"about_ca_system_score_gemma":0.0003264814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002487055,"about_ca_topic_score_gemma":0.00008513812,"domain_scores_codex":[0.9970886,0.0002581636,0.0004786337,0.0007839892,0.0009795409,0.0004111226],"domain_scores_gemma":[0.9979841,0.0001883362,0.0002333107,0.0005398114,0.0008835661,0.0001708772],"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":[0.00008393089,0.0001143601,0.00003902631,0.00005705541,0.00004737937,0.0001121264,0.0005711005,0.8248478,0.001661901,0.1698276,0.0007805079,0.001857212],"study_design_scores_gemma":[0.0003557514,0.0002961549,0.00001731308,0.0005655548,0.00001139378,0.00001031335,0.0004364882,0.9766051,0.01470997,0.00242097,0.00422354,0.000347498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006976278,0.00009511146,0.9503981,0.003346606,0.001567356,0.000323667,0.00001925577,0.0001081142,0.03716544],"genre_scores_gemma":[0.9887746,0.0001139769,0.001180272,0.001122877,0.0001256282,0.00006590817,0.00007771518,0.00002392138,0.008515128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9817983,"threshold_uncertainty_score":0.9999652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04755566164385049,"score_gpt":0.27826063322828,"score_spread":0.2307049715844295,"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."}}