{"id":"W4293155040","doi":"","title":"Dynamic Programming in Distributional Reinforcement Learning","year":2020,"lang":"en","type":"report","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Reinforcement learning; Computer science; Reinforcement; Dynamic programming; Artificial intelligence; Psychology; Algorithm; Social psychology","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":[0.002651446,0.001047733,0.001412094,0.0006607705,0.0004335918,0.001794464,0.001246696,0.001624762,0.00459839],"category_scores_gemma":[0.01400381,0.0004857215,0.0007130951,0.0009475477,0.002601959,0.002638199,0.002197821,0.003514169,0.0006588318],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001671175,"about_ca_system_score_gemma":0.001362072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00243281,"about_ca_topic_score_gemma":0.001726169,"domain_scores_codex":[0.9977909,0.001169476,0.00008041825,0.0004381095,0.0003547338,0.0001663859],"domain_scores_gemma":[0.9940687,0.004747282,0.0003041301,0.000260386,0.0003734334,0.0002461024],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006994484,0.00007944071,0.000589198,0.0001738537,0.00006462637,0.00008823476,0.0001125262,0.412027,0.0003995694,0.5478915,0.002761318,0.03574288],"study_design_scores_gemma":[0.00001545346,0.00002961592,0.00009887465,0.00002206495,0.000006565021,0.00001692543,0.00001267047,0.5566524,0.0001306463,0.4412144,0.001789836,0.0000105138],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009999163,0.001983284,0.9768018,0.001871544,0.0001461635,0.00003197272,0.00008739075,0.0001754989,0.008903245],"genre_scores_gemma":[0.7544508,0.00384403,0.2209702,0.001151044,0.0006992572,0.0005148914,0.0003479185,0.0003092625,0.01771267],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00459839,"threshold_uncertainty_score":0.01538312,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01766060272860948,"score_gpt":0.252790648297136,"score_spread":0.2351300455685265,"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."}}