{"id":"W2607014226","doi":"10.1109/tnnls.2017.2690910","title":"Learning to Predict Consequences as a Method of Knowledge Transfer in Reinforcement Learning","year":2017,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Reinforcement learning; Affordance; Robot; Human–computer interaction; Artificial intelligence; Robot learning; Semantics (computer science); Knowledge transfer; Transfer of learning; Task (project management); Knowledge management; Mobile robot","routes":{"ca_aff":true,"ca_fund":true,"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":[0.003869303,0.001110964,0.001094876,0.0006372769,0.0004530669,0.001040366,0.002371682,0.001557853,0.002593499],"category_scores_gemma":[0.01370038,0.0004761481,0.0007245685,0.0006320734,0.002445053,0.002548899,0.002024412,0.002478325,0.0003919857],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001157633,"about_ca_system_score_gemma":0.001102123,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002550864,"about_ca_topic_score_gemma":0.001980878,"domain_scores_codex":[0.9982571,0.0008473264,0.0001009204,0.0003022371,0.0003905595,0.0001019054],"domain_scores_gemma":[0.9936566,0.004472638,0.0004280683,0.0007528794,0.0005082213,0.0001816732],"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":[0.0001694616,0.0002402286,0.001585477,0.0001370558,0.0001228147,0.0001908527,0.0002875903,0.7918668,0.002592645,0.06750384,0.001246635,0.1340566],"study_design_scores_gemma":[0.00003562491,0.00007121575,0.0001191279,0.00001155196,0.00001521356,0.00002616628,0.00001091719,0.9601352,0.0009151027,0.03812099,0.0005260739,0.00001286712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01090441,0.0001250913,0.9862139,0.0002434602,0.00003548687,0.00009513648,0.00002060913,0.0003026674,0.002059265],"genre_scores_gemma":[0.7470756,0.0002417604,0.2491998,0.0002306209,0.00006889638,0.0005154939,0.00006184879,0.00007256464,0.002533395],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003869303,"threshold_uncertainty_score":0.02046311,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02503132052413058,"score_gpt":0.2901557942169168,"score_spread":0.2651244736927862,"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."}}