{"id":"W4398186376","doi":"10.1145/3605098.3635992","title":"Explainable Artificial Intelligence (XAI) Approach for Reinforcement Learning Systems","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009256321,0.0002099013,0.0001988498,0.0002143626,0.0002792522,0.001410698,0.0008281581,0.00008820331,0.00002429227],"category_scores_gemma":[0.0001087453,0.0001832174,0.0001129703,0.0005293974,0.00003729837,0.0007157383,0.0002748127,0.0002739483,0.0001789076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000137217,"about_ca_system_score_gemma":0.0001049385,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003012635,"about_ca_topic_score_gemma":2.146202e-7,"domain_scores_codex":[0.9978989,0.00005111371,0.0005117569,0.0005577938,0.00043607,0.0005443094],"domain_scores_gemma":[0.9990044,0.0002411841,0.00007770122,0.0004612458,0.0001111917,0.0001042808],"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":[0.000001977705,0.000005312395,0.000002236095,0.0001695432,0.0000172891,0.000002837622,0.0003041416,0.5688107,0.0000553596,0.426723,0.0005556653,0.00335198],"study_design_scores_gemma":[0.00002876856,0.0002086209,3.937417e-7,0.00006503908,0.00000922395,0.00001233005,0.0005397657,0.9751132,0.001293606,0.0007911613,0.02169932,0.0002385567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00001235477,0.0002386027,0.9647518,0.0001533369,0.001075897,0.0006619794,1.936151e-7,0.0008889484,0.03221686],"genre_scores_gemma":[0.8228628,0.00002662383,0.143843,0.00007235365,0.0002825597,0.0002677343,0.00002139821,0.0000321529,0.03259138],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8228504,"threshold_uncertainty_score":0.9996259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05129248742520472,"score_gpt":0.2827490939527325,"score_spread":0.2314566065275278,"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."}}