{"id":"W3015230978","doi":"10.48550/arxiv.2004.03761","title":"Adaptive Transformers in RL","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Transformer; Computer science; Computation; Replicate; Reinforcement learning; Artificial intelligence; Computer engineering; Machine learning; Voltage; Electrical engineering; Engineering; Algorithm","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001591101,0.0002976471,0.0003346352,0.0002791754,0.00006549135,0.00008750462,0.001885228,0.0002519853,0.00002666844],"category_scores_gemma":[0.00002732102,0.0003702835,0.0001827974,0.0007834282,0.00008466337,0.0003887591,0.001138642,0.0009992833,0.0001744041],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003018099,"about_ca_system_score_gemma":0.0002586398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001254275,"about_ca_topic_score_gemma":0.00003117639,"domain_scores_codex":[0.9981843,0.0001134448,0.0002265089,0.0009712993,0.0001219099,0.0003825511],"domain_scores_gemma":[0.9988887,0.0000820681,0.0001699237,0.0006282572,0.00006348939,0.0001675521],"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":[0.00002050491,0.00001654336,0.000776139,0.00003433245,0.000038929,0.0003283209,0.0005572415,0.9203932,0.000006954145,0.07736275,0.00009091105,0.0003742082],"study_design_scores_gemma":[0.0004438182,0.00008789793,0.0008659807,0.00007961897,0.00002203513,0.000001277319,0.0001242096,0.9903913,0.00004006019,0.007093617,0.0004648787,0.0003853334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007019959,0.00001795831,0.9774019,0.0003044322,0.0004021693,0.000312357,0.000003079129,0.0002253431,0.01431277],"genre_scores_gemma":[0.9951912,0.0001123163,0.003557074,0.0001704646,0.00003402262,7.317403e-7,0.000008166357,0.00001673729,0.0009093448],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9881712,"threshold_uncertainty_score":0.9998749,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1102922021503649,"score_gpt":0.1882050874701803,"score_spread":0.07791288531981543,"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."}}