{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009458574,0.001425829,0.001703621,0.0005288871,0.000569667,0.003072043,0.002776959,0.002584404,0.0035432],"category_scores_gemma":[0.04405364,0.0008905139,0.0008161795,0.0006522251,0.002087135,0.007187878,0.002744056,0.005931761,0.0003776323],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002361526,"about_ca_system_score_gemma":0.001442788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002336824,"about_ca_topic_score_gemma":0.001640695,"domain_scores_codex":[0.9963281,0.00176322,0.0002166239,0.000671584,0.0007815782,0.0002388608],"domain_scores_gemma":[0.9869655,0.009655801,0.0009275967,0.001070899,0.0009411781,0.0004389817],"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":[0.0002717079,0.0001297895,0.002424433,0.0002529948,0.0001735598,0.0001729837,0.0005007355,0.6208383,0.003279857,0.3202327,0.00139837,0.05032448],"study_design_scores_gemma":[0.00002432292,0.00007708688,0.0001646494,0.00003593146,0.00002184189,0.00004429092,0.00002183314,0.9127333,0.001056184,0.0844932,0.001306514,0.00002088003],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0202206,0.001041053,0.9728387,0.001521038,0.0001319495,0.00003910276,0.00002195368,0.000190462,0.003995153],"genre_scores_gemma":[0.7865157,0.0008960734,0.2070545,0.0006386882,0.0002248878,0.0001119701,0.00004846779,0.000292516,0.004217025],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009458574,"threshold_uncertainty_score":0.0500223,"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."}}