{"id":"W4407253672","doi":"10.1007/978-981-97-8702-9_20","title":"Feature-Based Explainable Reinforcement Learning in Environments with Multiple Sources of Risk","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Reinforcement learning; Feature (linguistics); Artificial intelligence; Reinforcement; Engineering","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"],"consensus_categories":[],"category_scores_codex":[0.00102223,0.0005851423,0.0006673134,0.001367517,0.0002519428,0.0002493623,0.002648032,0.0003042465,0.00001083509],"category_scores_gemma":[0.0002903889,0.0005169078,0.0001105439,0.0008165642,0.0005965838,0.0004427404,0.001092803,0.00146835,0.000008994716],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005333312,"about_ca_system_score_gemma":0.0005994876,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008578223,"about_ca_topic_score_gemma":0.00007502524,"domain_scores_codex":[0.9959362,0.00008151362,0.0005850417,0.001267667,0.001377566,0.0007520198],"domain_scores_gemma":[0.9966669,0.001085341,0.0007601152,0.001278442,0.00009588432,0.0001132984],"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":[0.00002381033,0.00001760454,0.006739751,0.0000661714,0.0000134055,0.00004332491,0.00058764,0.9568416,0.00002400088,0.001056617,0.000005592628,0.03458041],"study_design_scores_gemma":[0.0009099356,0.0003929831,0.0007200005,0.001030386,0.00001301767,0.00000515799,9.607523e-7,0.9909505,0.002480793,0.0009175166,0.002049192,0.0005295188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002120041,0.0001775809,0.9965682,0.00017977,0.0003238896,0.0005311975,0.000001320676,0.00008066934,0.001925384],"genre_scores_gemma":[0.6334063,0.00007217465,0.3631029,0.0003553917,0.00006921551,0.0000205609,0.00001372667,0.00003836713,0.002921291],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6334653,"threshold_uncertainty_score":0.9997283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.00814257528352944,"score_gpt":0.2077444555139946,"score_spread":0.1996018802304652,"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."}}