{"id":"W2570416447","doi":"10.1007/978-3-642-33093-3_30","title":"Multi-timescale Nexting in a Reinforcement Learning Robot","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Reinforcement learning; Robot; Artificial intelligence; Human–computer interaction","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":[0.0003795168,0.0003349539,0.0005418068,0.0001842938,0.0006665486,0.0004537464,0.001122017,0.0009742606,0.003905439],"category_scores_gemma":[0.0006853846,0.0003024286,0.0003398766,0.0001721246,0.0005819236,0.0008166541,0.001054805,0.0009557451,0.0004249052],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004214355,"about_ca_system_score_gemma":0.0005112343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002435995,"about_ca_topic_score_gemma":0.002453148,"domain_scores_codex":[0.9998673,0.00002379708,0.000007498102,0.00004705486,0.00003105708,0.00002322198],"domain_scores_gemma":[0.9997255,0.0001109393,0.00002565018,0.00003677507,0.00003849109,0.00006266558],"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":[0.0005910799,0.0003049256,0.001386454,0.000151222,0.00005494749,0.0006740193,0.0002099686,0.7656533,0.05705065,0.034015,0.002190212,0.1377182],"study_design_scores_gemma":[0.00001861154,0.0001060446,0.0001965698,0.00000604558,0.000009284669,0.00005098835,0.00001188601,0.9906227,0.002411463,0.00557065,0.0009841064,0.00001172115],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1303961,0.0005059002,0.8500818,0.0006681018,0.0002906252,0.00008788554,0.00005122932,0.001646502,0.01627183],"genre_scores_gemma":[0.8836704,0.0001461264,0.106187,0.00009702831,0.0000325916,0.00006122394,0.00002947131,0.00006744545,0.009708718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003905439,"threshold_uncertainty_score":0.01306504,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02659981860661804,"score_gpt":0.2579270346567551,"score_spread":0.2313272160501371,"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."}}