{"id":"W7124320264","doi":"10.65109/jazo1666","title":"A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms","year":2022,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Discounting; Perspective (graphical); Representation (politics); Term (time); Trajectory; Task (project management); Value (mathematics); Empirical research","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001961989,0.0005016681,0.0005214893,0.0004152177,0.001194096,0.0006850871,0.00246438,0.0001106221,0.006860349],"category_scores_gemma":[0.0001970593,0.0005582945,0.0002138984,0.001515045,0.0001701028,0.001006404,0.006336753,0.001206291,0.0005255177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001499956,"about_ca_system_score_gemma":0.0003404136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003750695,"about_ca_topic_score_gemma":0.00004981717,"domain_scores_codex":[0.9937825,0.0006163981,0.001131185,0.001217042,0.001768552,0.001484325],"domain_scores_gemma":[0.9975674,0.0005166561,0.0003017596,0.001285055,0.00009653056,0.0002325822],"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":[0.00002452956,0.0001831028,0.01747577,0.0001009563,0.00004440653,0.0002755389,0.008320481,0.9598132,0.0002423673,0.006911957,0.001249761,0.005357902],"study_design_scores_gemma":[0.0009469313,0.0002634933,0.002155929,0.00006163344,0.00002071159,0.0001025333,0.001400398,0.9833219,0.0001897366,0.000231854,0.01057818,0.0007267107],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04237117,0.0005092598,0.931664,0.002547257,0.003308687,0.000753641,0.000004148802,0.0002026954,0.01863912],"genre_scores_gemma":[0.9265905,0.00004457466,0.02394271,0.001590852,0.0001742568,0.00009267841,0.00001263849,0.00006407808,0.04748769],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9077213,"threshold_uncertainty_score":0.9996868,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01937459572138,"score_gpt":0.2547291520579243,"score_spread":0.2353545563365443,"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."}}