{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001232419,0.0008594486,0.0007583576,0.0008837247,0.0006353983,0.0008314013,0.003572336,0.0004041965,0.00003182645],"category_scores_gemma":[0.000552439,0.0008081136,0.0002803324,0.0006920395,0.0007063178,0.0004722483,0.0009262704,0.001301766,0.00005778035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001121607,"about_ca_system_score_gemma":0.001394257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001286184,"about_ca_topic_score_gemma":0.000005816342,"domain_scores_codex":[0.9944353,0.00004146463,0.0009117824,0.0017664,0.001712593,0.001132525],"domain_scores_gemma":[0.9958643,0.001075618,0.0006743161,0.001677891,0.0004506843,0.0002571411],"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":[0.00002398967,0.00001842091,0.00001336681,0.00007326604,0.00001698473,0.00003122017,0.000188458,0.9098111,0.00001676616,0.06443661,0.00001560357,0.0253542],"study_design_scores_gemma":[0.001005018,0.001398982,0.00001260319,0.0007584625,0.00001831688,0.000008807978,1.903664e-7,0.9570512,0.002609206,0.03298208,0.003304814,0.0008503629],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000009171076,0.00006600611,0.9935191,0.001266911,0.002079223,0.001061247,0.000007080265,0.0003855609,0.001605679],"genre_scores_gemma":[0.3510524,0.00002289473,0.643036,0.003237355,0.0008280806,0.00006553116,0.0001830725,0.0001157777,0.00145883],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3510433,"threshold_uncertainty_score":0.999437,"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."}}