{"id":"W1548867233","doi":"10.1007/978-3-540-30115-8_33","title":"Sparse Distributed Memories for On-Line Value-Based Reinforcement Learning","year":2004,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Reinforcement learning; A priori and a posteriori; Bellman equation; Line (geometry); Function (biology); Scheme (mathematics); Dynamic random-access memory; Distributed computing; Artificial intelligence; Mathematical optimization; Semiconductor memory; Computer hardware","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":[0.0005128952,0.0006754221,0.001105578,0.0002527729,0.0002981182,0.0008845243,0.001515439,0.0009264607,0.006860473],"category_scores_gemma":[0.002233867,0.0003885601,0.0003599785,0.0005250829,0.0006667335,0.001123883,0.001174667,0.00216249,0.000712018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006177497,"about_ca_system_score_gemma":0.0005345953,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001957062,"about_ca_topic_score_gemma":0.003535859,"domain_scores_codex":[0.9997298,0.00006988362,0.00001882809,0.00005924252,0.00008151738,0.00004072196],"domain_scores_gemma":[0.9990923,0.0005368069,0.00006175548,0.0001337279,0.0001376835,0.00003763865],"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":[0.000214794,0.0001489664,0.0002461557,0.000139529,0.00005858274,0.00006860024,0.00007093942,0.7213832,0.003930598,0.05967814,0.004289491,0.209771],"study_design_scores_gemma":[0.00001723549,0.00002511157,0.00003263515,0.000004866611,0.000005104475,0.00001116827,0.000003840272,0.9724585,0.0005555052,0.02644807,0.0004339656,0.000003915335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01083771,0.0002835518,0.9847698,0.0001510293,0.00008832184,0.00003718337,0.00004649168,0.0004566213,0.003329371],"genre_scores_gemma":[0.8112323,0.0004382778,0.178263,0.0001881378,0.0001086238,0.0002755585,0.000168267,0.0001125382,0.009213357],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006860473,"threshold_uncertainty_score":0.02295053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03030559736602707,"score_gpt":0.2671672585046126,"score_spread":0.2368616611385856,"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."}}