{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009757961,0.0005315646,0.0003736292,0.0002818964,0.000269255,0.0005408365,0.0007602887,0.0005938666,0.0008795874],"category_scores_gemma":[0.003003943,0.0004642393,0.000364404,0.0002124003,0.0007587615,0.0007653098,0.000604899,0.001085574,0.0001023475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006720155,"about_ca_system_score_gemma":0.0007037843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005225625,"about_ca_topic_score_gemma":0.005102076,"domain_scores_codex":[0.9997343,0.00008792813,0.00001786966,0.00007256377,0.00005521788,0.00003212281],"domain_scores_gemma":[0.9989812,0.0005852581,0.0001513652,0.0001122126,0.0001021279,0.00006776812],"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":[0.0001363195,0.00007503645,0.002166195,0.00005603118,0.00006983641,0.00009035091,0.0001270582,0.9661307,0.005078782,0.003760396,0.0001650338,0.02214426],"study_design_scores_gemma":[0.000005915713,0.00002877052,0.000241838,0.000001543256,0.000005809226,0.000007630158,0.000003045505,0.997916,0.0005425499,0.001188005,0.00005534115,0.000003508616],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2997589,0.0002570288,0.695957,0.0002745573,0.00004285205,0.00009693766,0.00003238581,0.0006608088,0.002919525],"genre_scores_gemma":[0.9776471,0.0000394276,0.02173915,0.00001672745,0.000003647739,0.00004833167,0.00001482679,0.00001355246,0.0004772681],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005225625,"threshold_uncertainty_score":0.0103904,"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."}}