{"id":"W2132622533","doi":"10.5555/2031678.2031726","title":"Horde: a scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction","year":2011,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":305,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Reinforcement learning; Function (biology); Scalability; Temporal difference learning; Modular design; Architecture; Robot; Robot learning; Robotics; Machine learning; Unsupervised learning; Mobile robot","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":[0.0002363391,0.0002087182,0.000221136,0.000143473,0.0001930822,0.000153298,0.0006470305,0.0001090315,0.0004482751],"category_scores_gemma":[0.0001457549,0.000186533,0.0001141296,0.0002492749,0.00003124888,0.0004170176,0.0002340571,0.0002836924,0.0006485887],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000677533,"about_ca_system_score_gemma":0.00005828257,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002822767,"about_ca_topic_score_gemma":0.000009845169,"domain_scores_codex":[0.9985661,0.0001130016,0.0002922173,0.0004717264,0.0001735085,0.0003834594],"domain_scores_gemma":[0.9987479,0.0003474203,0.0001238735,0.000507862,0.0001525395,0.0001203571],"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":[0.0007093608,0.0007532553,0.008014528,0.0002994676,0.0007505495,0.00003762201,0.05778679,0.5234396,0.1183871,0.03280865,0.02131783,0.2356953],"study_design_scores_gemma":[0.0006285246,0.000380699,0.0009631351,0.00004712152,0.00001921573,0.000004833458,0.0001057292,0.9648424,0.007417363,0.0006224482,0.02464423,0.0003243015],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01438535,0.00001513361,0.9193181,0.00008789951,0.000447585,0.0003525553,0.000001177627,0.0005995876,0.0647926],"genre_scores_gemma":[0.2669595,0.00002739312,0.7031164,0.0001258418,0.0003045433,0.00006440374,0.00003903906,0.00005687371,0.02930601],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4414028,"threshold_uncertainty_score":0.8336512,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03268646550292204,"score_gpt":0.2583288463899193,"score_spread":0.2256423808869972,"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."}}