{"id":"W70929694","doi":"","title":"Temporal-difference networks with history","year":2005,"lang":"en","type":"article","venue":"","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Formalism (music); Artificial intelligence; Markov process; Observable; Theoretical computer science; Temporal difference learning; Simple (philosophy); Machine learning; Mathematics; Reinforcement learning; Epistemology","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":[],"consensus_categories":[],"category_scores_codex":[0.00009873931,0.0001129487,0.0001004756,0.00003713723,0.00004390007,0.00005155837,0.0005774254,0.00003889708,0.00007539585],"category_scores_gemma":[0.000003108023,0.00008094314,0.00002220129,0.0001072739,0.00004266839,0.0002618961,0.00007428581,0.0001389877,0.00007510856],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000855827,"about_ca_system_score_gemma":0.00009293496,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005659199,"about_ca_topic_score_gemma":0.00005779922,"domain_scores_codex":[0.9991733,0.00002183465,0.0001220285,0.000293527,0.0001585408,0.0002307],"domain_scores_gemma":[0.9993455,0.00002291633,0.00004016178,0.0004293678,0.00005512435,0.0001069767],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001855048,0.000189026,0.00373357,0.00001073705,0.00002643384,0.00002577976,0.0006663254,0.02136713,0.0002320182,0.4412244,0.05272519,0.4797809],"study_design_scores_gemma":[0.0001462978,0.00007233064,0.001069498,0.00001193342,0.000002363211,0.00001776245,0.000003132675,0.9738688,0.00007475052,0.0004463351,0.02408097,0.0002058274],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001696026,0.0003159792,0.9639021,0.0009756817,0.0000875434,0.00004144127,7.184232e-8,0.0003348684,0.0326463],"genre_scores_gemma":[0.821064,0.00001228193,0.1689528,0.002063564,0.00008151227,0.000006264501,6.480633e-7,0.000004316395,0.007814589],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9525017,"threshold_uncertainty_score":0.3300765,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02201791365706475,"score_gpt":0.2084485591808123,"score_spread":0.1864306455237476,"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."}}