{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002147078,0.0007535354,0.0007308921,0.001384022,0.0003426333,0.0006846936,0.003698632,0.0004465904,0.00006992231],"category_scores_gemma":[0.0003770676,0.000754811,0.0001444083,0.000916196,0.0004675264,0.001244985,0.002766426,0.002235532,0.0001983013],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008053603,"about_ca_system_score_gemma":0.0004520614,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005567269,"about_ca_topic_score_gemma":0.00003887051,"domain_scores_codex":[0.9943247,0.00008009119,0.001149722,0.00153588,0.00142409,0.001485548],"domain_scores_gemma":[0.9967717,0.0006496118,0.000668968,0.001444183,0.0001887317,0.0002768116],"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":[0.000002577453,0.00001459154,0.0003927162,0.00003316128,0.000006857413,0.0000392576,0.001171905,0.8278152,0.0001944046,0.001550746,0.000002331887,0.1687762],"study_design_scores_gemma":[0.0004777134,0.0001751758,0.0003059205,0.0005895019,0.000006945508,0.00003630843,5.081247e-7,0.9942927,0.0003495927,0.001080532,0.00185841,0.000826651],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002563176,0.0005248804,0.9927851,0.0002377763,0.001398273,0.0005560816,2.236553e-7,0.000249608,0.004222414],"genre_scores_gemma":[0.2856719,0.0001060207,0.7100174,0.000747437,0.0004258689,0.00001843298,0.000008526185,0.00007313938,0.002931257],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2856463,"threshold_uncertainty_score":0.9994903,"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."}}