{"id":"W2898050260","doi":"10.1109/ijcnn.2018.8489122","title":"Mixing Habits and Planning for Multi-Step Target Reaching Using Arbitrated Predictive Actor-Critic","year":2018,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Task (project management); Control (management); Model predictive control; Internal model; Controller (irrigation); Artificial intelligence; Work (physics); Engineering","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":[0.0004068277,0.0001842813,0.0001878408,0.000133348,0.0004425364,0.0002925991,0.0003753304,0.00008571735,0.000004864488],"category_scores_gemma":[0.0003699919,0.0001740851,0.00003886284,0.0001971161,0.00009472334,0.0008224455,0.0002256641,0.0001880952,0.000004111797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007281542,"about_ca_system_score_gemma":0.00006390902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004345084,"about_ca_topic_score_gemma":0.000002421986,"domain_scores_codex":[0.9985923,0.00005979963,0.0002739433,0.0004298788,0.0002035512,0.0004405603],"domain_scores_gemma":[0.9990544,0.0002235928,0.0001134778,0.000283921,0.0002099783,0.0001146046],"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":[0.0001602103,0.0001722646,0.07332642,0.0004586152,0.0004612585,0.00005676179,0.0368831,0.7810611,0.06860001,0.03153447,0.001255,0.006030781],"study_design_scores_gemma":[0.0005286758,0.0001988279,0.00123474,0.0001253349,0.00001264076,0.00001344704,0.0002382902,0.9935275,0.00353781,0.00009822184,0.0002706248,0.0002139158],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04659687,0.00004081296,0.9512708,0.00004321584,0.0004686912,0.0003160461,0.000001435296,0.0002723058,0.000989793],"genre_scores_gemma":[0.4919904,4.807045e-7,0.5075933,0.0001634485,0.0001193085,0.000004815581,0.000002460459,0.00001107595,0.00011473],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4453935,"threshold_uncertainty_score":0.7098985,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07409115597081546,"score_gpt":0.3278817011003397,"score_spread":0.2537905451295242,"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."}}