{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001572351,0.0003496916,0.0005770873,0.0003647404,0.001281761,0.0005402245,0.0007952232,0.000192729,0.00001262791],"category_scores_gemma":[0.0001091872,0.0003332397,0.0001208707,0.000355069,0.0001575377,0.0005542204,0.00002170572,0.001774574,0.00001425749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007317388,"about_ca_system_score_gemma":0.00006410164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007569296,"about_ca_topic_score_gemma":0.00003588336,"domain_scores_codex":[0.9966539,0.0009540597,0.0007486114,0.0006308125,0.0004264558,0.0005861536],"domain_scores_gemma":[0.9981843,0.0006530946,0.0002998382,0.0005170497,0.0001208979,0.0002248234],"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":[0.00006023516,0.00002294904,0.001052864,0.00007588912,0.00004669173,0.000016373,0.002461965,0.9746279,0.0005033698,0.0003727494,0.000006847082,0.02075218],"study_design_scores_gemma":[0.000690615,0.001698657,0.0005265536,0.0005011404,0.00002547544,0.00005635716,0.0004762334,0.9941812,0.0004026812,0.000002754659,0.001110088,0.0003282494],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03332894,0.0001333171,0.9633189,0.0001761372,0.001017509,0.0005401285,2.688114e-7,0.0001807817,0.001304003],"genre_scores_gemma":[0.9943551,0.0001374901,0.001070332,0.00003550247,0.00007847206,0.00007472112,0.000001238132,0.00003289046,0.004214266],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9622486,"threshold_uncertainty_score":0.999912,"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."}}