{"id":"W4405792203","doi":"10.18280/isi.290612","title":"Waste Objects Segregation Using Deep Reinforcement Learning with Deep Q Networks","year":2024,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Smart Systems and Machine Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Reinforcement; Deep learning; Computer science; Engineering; Structural engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006516082,0.0006402688,0.0005840887,0.000346568,0.0003517026,0.0007062932,0.0009581813,0.0007331179,0.001376719],"category_scores_gemma":[0.001267378,0.0003465735,0.0004728745,0.0003071498,0.0005389279,0.0007984271,0.0007900632,0.0008917456,0.0002821018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001077139,"about_ca_system_score_gemma":0.001067188,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008667652,"about_ca_topic_score_gemma":0.007871868,"domain_scores_codex":[0.999786,0.00004127004,0.00001094442,0.00006525664,0.00005509843,0.00004153221],"domain_scores_gemma":[0.9995422,0.0001693945,0.00007542033,0.00003475678,0.0001419304,0.00003627517],"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":[0.0001356173,0.0001407619,0.001898087,0.00004049901,0.00003988128,0.00007832847,0.00004387301,0.8940601,0.007307091,0.002967411,0.0008253927,0.0924629],"study_design_scores_gemma":[0.000003021,0.00001284842,0.00005518549,0.000001270884,0.000002321976,0.00000314237,0.000001557109,0.9985325,0.0006671458,0.0006256977,0.00009359344,0.000001651844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06198324,0.0002123225,0.9340523,0.0002432016,0.00005759392,0.00005334375,0.00004336693,0.0009298269,0.002424817],"genre_scores_gemma":[0.9160913,0.00009751683,0.08085568,0.0001597559,0.00002195909,0.00006301735,0.0000797879,0.00003947637,0.002591429],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008667652,"threshold_uncertainty_score":0.01723439,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009272319328961541,"score_gpt":0.2209461445211481,"score_spread":0.2116738251921865,"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."}}