{"id":"W4416464763","doi":"10.1007/978-981-95-4367-0_40","title":"An Ensemble Method with Plans-Managed Policy for Proximal Policy Optimization","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Ensemble learning; Policy learning; Optimization algorithm; Optimization problem; Ensemble forecasting","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":[0.001067325,0.0006069088,0.000575218,0.002245497,0.0004367622,0.0009731015,0.003776697,0.0003407993,0.000004007311],"category_scores_gemma":[0.0002738918,0.0005340276,0.0001066772,0.001475037,0.0003470277,0.0009201613,0.0007483684,0.0006204875,0.000004199759],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005470145,"about_ca_system_score_gemma":0.002554978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006621089,"about_ca_topic_score_gemma":0.00004669538,"domain_scores_codex":[0.9959715,0.0000737294,0.0005313428,0.00163214,0.0009252517,0.0008660621],"domain_scores_gemma":[0.9966006,0.0006431384,0.0003992897,0.001735236,0.0004240891,0.0001976581],"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":[0.00001560443,0.00001255943,0.00000756716,0.00005994012,0.00001440499,0.000009211824,0.0003454157,0.7622108,0.00002694679,0.09248789,0.00001331155,0.1447963],"study_design_scores_gemma":[0.000457046,0.0006031378,0.00001185008,0.0002885636,0.00001476352,0.00002967796,2.01644e-7,0.9783231,0.0005214324,0.01810325,0.001067993,0.0005789774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[8.562074e-7,0.00002823241,0.9899431,0.001768251,0.0004267686,0.001129636,0.0000075759,0.0002877857,0.006407803],"genre_scores_gemma":[0.003976039,0.00001456414,0.991349,0.002152674,0.0006490669,0.00003509691,0.00002752715,0.0000446442,0.001751366],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2161123,"threshold_uncertainty_score":0.9997112,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01507838733675685,"score_gpt":0.2931504114345274,"score_spread":0.2780720240977705,"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."}}