{"id":"W2987502141","doi":"10.1609/aaai.v34i04.6027","title":"Gamma-Nets: Generalizing Value Estimation over Timescale","year":2020,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates; Alberta Machine Intelligence Institute; Compute Canada","keywords":"Estimator; Reinforcement learning; Computer science; A priori and a posteriori; Bellman equation; Representation (politics); Function (biology); Value (mathematics); Artificial intelligence; Algorithm; Machine learning; Mathematical optimization; Mathematics; Statistics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005726881,0.0005061956,0.0005391754,0.0001857937,0.0002280389,0.0008937802,0.004572368,0.0003138866,0.00007962045],"category_scores_gemma":[0.0007823629,0.0004283333,0.0002832534,0.0005868204,0.000256361,0.000457021,0.00316744,0.00121039,0.0002069282],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001520717,"about_ca_system_score_gemma":0.0002835644,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007476129,"about_ca_topic_score_gemma":0.000001372014,"domain_scores_codex":[0.9963106,0.00004190704,0.001043231,0.001008128,0.001113289,0.0004828514],"domain_scores_gemma":[0.9971673,0.0001097698,0.001230986,0.0007080095,0.0006259846,0.0001578929],"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":[0.00002339379,0.0000447695,0.00005302997,0.0001823301,0.00004042762,8.806472e-7,0.001342733,0.3025362,0.007771146,0.665993,0.0005688923,0.0214432],"study_design_scores_gemma":[0.00001826322,0.00009716012,0.00006341063,0.0005368904,0.00002633051,0.000001791164,0.00004773982,0.750271,0.1066231,0.1418237,0.0001589209,0.000331731],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009524936,0.00003597411,0.9629599,0.008237336,0.001479892,0.0008963352,0.000006933385,0.0003226424,0.01653607],"genre_scores_gemma":[0.9468061,0.00006230739,0.05161556,0.000680158,0.0001708309,0.00004633326,0.000004998682,0.00003781425,0.0005758411],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9372812,"threshold_uncertainty_score":0.9998168,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09424233049296664,"score_gpt":0.3121223173230463,"score_spread":0.2178799868300797,"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."}}