{"id":"W2902729397","doi":"10.1613/jair.1.11263","title":"Grounding Language for Transfer in Deep Reinforcement Learning","year":2018,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Transfer of learning; Representation (politics); Artificial intelligence; Task (project management); Differentiable function; Domain (mathematical analysis); Component (thermodynamics); Meaning (existential); Machine learning","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":[0.006784916,0.0001218318,0.000236807,0.0009064999,0.0003003027,0.0003595669,0.001219722,0.00008679832,0.00008351458],"category_scores_gemma":[0.001443207,0.0001087328,0.0001216975,0.001085193,0.0002003744,0.000704085,0.0001497349,0.0008713073,0.00007713437],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000260527,"about_ca_system_score_gemma":0.0002037926,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000365328,"about_ca_topic_score_gemma":0.0000443362,"domain_scores_codex":[0.9968134,0.0002717424,0.000912776,0.0002266861,0.001082085,0.0006933144],"domain_scores_gemma":[0.9976851,0.0007932528,0.0001369741,0.0002678738,0.0009700863,0.0001467324],"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":[0.0002624663,0.00008899708,0.0002900127,0.00005876012,0.0000413569,0.00007738389,0.0215409,0.6470612,0.01701873,0.1128169,0.00007751374,0.2006658],"study_design_scores_gemma":[0.0001018664,0.002064159,0.00004927946,0.0001373376,0.0000039044,0.00002520674,0.004052348,0.9231563,0.06543958,0.003648038,0.00117415,0.0001478479],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02865824,0.00007677845,0.9691628,0.0004625104,0.0004422957,0.0002594348,5.030151e-8,0.00001716379,0.0009207677],"genre_scores_gemma":[0.9842557,0.00005766374,0.01480148,0.00003586334,0.0005320308,0.000008064632,4.87503e-7,0.00001397197,0.0002947912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9555974,"threshold_uncertainty_score":0.4433995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1503297529386259,"score_gpt":0.4297375410971567,"score_spread":0.2794077881585307,"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."}}