{"id":"W2998494185","doi":"10.1609/aaai.v34i04.6027","title":"Gamma-Nets: Generalizing Value Estimation over Timescale","year":2020,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"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":"Reinforcement learning; Computer science; Estimator; Bellman equation; Abstraction; Artificial intelligence; Scalability; Function (biology); Set (abstract data type); Temporal difference learning; Machine learning; Value (mathematics); Representation (politics); Key (lock); Markov decision process; Mathematical optimization; Markov process; 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":[],"consensus_categories":[],"category_scores_codex":[0.00009851009,0.00009645921,0.00009260619,0.00003095758,0.00007204395,0.0001892054,0.0004951943,0.00003811914,0.0001485187],"category_scores_gemma":[0.00006579402,0.00008930387,0.000040571,0.0002439926,0.00001482636,0.0005130352,0.0002243146,0.00009592414,0.0005179203],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002764711,"about_ca_system_score_gemma":0.00002842075,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001558984,"about_ca_topic_score_gemma":1.815606e-7,"domain_scores_codex":[0.9990727,0.00003308143,0.0001831489,0.0002411325,0.0002791943,0.0001908007],"domain_scores_gemma":[0.9994971,0.00003741172,0.00006142011,0.0002702659,0.00002644194,0.000107347],"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":[8.242554e-7,0.000003115929,0.0001802132,0.000006528704,0.000006036397,0.000003022661,0.0002998788,0.9381354,0.0005816999,0.05027028,0.005904497,0.004608487],"study_design_scores_gemma":[0.000146371,0.00004784989,0.0003731671,0.000005593009,0.000002938432,0.000001845551,0.000004040523,0.9859321,0.001614237,0.0002319662,0.01152107,0.0001188478],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001038891,0.00001635414,0.9730752,0.003561148,0.0001347134,0.00008552409,1.187725e-7,0.0003616936,0.02172639],"genre_scores_gemma":[0.3201762,0.000005283721,0.6680779,0.008259829,0.0001038375,0.000004334412,0.000005603736,0.00001388023,0.003353073],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3191373,"threshold_uncertainty_score":0.6656991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02043068963763373,"score_gpt":0.2437083033784362,"score_spread":0.2232776137408025,"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."}}