{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007064655,0.0006491038,0.0009000268,0.0002527141,0.0002485835,0.0006800992,0.001246858,0.001151065,0.002348882],"category_scores_gemma":[0.003551481,0.000432662,0.0004580336,0.0003389024,0.0007759671,0.00118874,0.001342421,0.001642437,0.0002051058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007735854,"about_ca_system_score_gemma":0.000489458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002353717,"about_ca_topic_score_gemma":0.002534623,"domain_scores_codex":[0.9997479,0.00007854207,0.00001178542,0.00005461525,0.00006440774,0.00004275066],"domain_scores_gemma":[0.9982826,0.00129052,0.0001557631,0.00009947262,0.0001046039,0.00006704119],"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":[0.00005139863,0.00002283697,0.0002532128,0.00003436494,0.00002273792,0.00005669182,0.00004530392,0.9501279,0.0009171403,0.02264285,0.0004927444,0.02533278],"study_design_scores_gemma":[0.000004544685,0.00001240929,0.00004984446,0.000002289926,0.000002570822,0.000007839118,0.000001729676,0.9880591,0.0001080695,0.01165568,0.0000930941,0.000002885996],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03048264,0.0001948926,0.9665604,0.0002002188,0.00003132212,0.00001689423,0.00003269424,0.0002737251,0.002207347],"genre_scores_gemma":[0.8976675,0.0001986234,0.09723794,0.00005840141,0.00004112878,0.00008207127,0.00006342497,0.0000772503,0.0045736],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002353717,"threshold_uncertainty_score":0.00785774,"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."}}