{"id":"W4405602545","doi":"10.1109/icsme58944.2024.00019","title":"Toward Debugging Deep Reinforcement Learning Programs with RLExplorer","year":2024,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Debugging; Reinforcement learning; Computer science; Algorithmic program debugging; Programming language; Artificial intelligence; Human–computer interaction; Software 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":[0.002295909,0.001125924,0.0006174449,0.0004695679,0.0003805693,0.0009514866,0.001978247,0.001394629,0.005615567],"category_scores_gemma":[0.01353574,0.0008977519,0.0005937396,0.0002623509,0.001077228,0.002463748,0.001778348,0.002777114,0.0008075698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007686001,"about_ca_system_score_gemma":0.001324257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003364702,"about_ca_topic_score_gemma":0.007979429,"domain_scores_codex":[0.9987932,0.0005276309,0.000065757,0.0002727387,0.0002317049,0.0001089192],"domain_scores_gemma":[0.9938287,0.004465814,0.00025023,0.0008342074,0.0004704205,0.0001505847],"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":[0.0009907348,0.0003674844,0.004573963,0.0002933051,0.0001237236,0.00030901,0.0002951539,0.5746325,0.01234392,0.03677638,0.008182513,0.3611113],"study_design_scores_gemma":[0.00002488215,0.00002458626,0.00006000422,0.00001248583,0.000009657195,0.00001721515,0.00001345595,0.9849157,0.004018503,0.01028105,0.0006179776,0.000004424887],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02716178,0.0001074055,0.9595642,0.0002995758,0.00006881318,0.00004316177,0.00008391796,0.01093129,0.001739729],"genre_scores_gemma":[0.4776283,0.00005958354,0.5186523,0.0002802264,0.00002314942,0.00007011149,0.000167264,0.000994714,0.002124448],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005615567,"threshold_uncertainty_score":0.01878595,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03009305622501012,"score_gpt":0.2465751540760077,"score_spread":0.2164820978509975,"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."}}