{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001143246,0.0009228398,0.0007255414,0.0004734139,0.0003137576,0.001256498,0.001079441,0.0008217589,0.006515888],"category_scores_gemma":[0.006698966,0.0004460111,0.0005709123,0.0003826077,0.001822337,0.002200723,0.001884173,0.001891659,0.001228334],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009250402,"about_ca_system_score_gemma":0.001038028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002826863,"about_ca_topic_score_gemma":0.002998665,"domain_scores_codex":[0.9991849,0.0002946193,0.00005705961,0.0002162326,0.0001633296,0.00008393366],"domain_scores_gemma":[0.9980199,0.001321174,0.0001155596,0.0002669854,0.0001875262,0.00008884735],"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":[0.0002865435,0.00005663304,0.000858805,0.0002467824,0.00007082068,0.0001759207,0.000245022,0.6021633,0.008726371,0.2604078,0.003673291,0.1230887],"study_design_scores_gemma":[0.00003336083,0.00005659486,0.00008105503,0.00001651474,0.00001375504,0.00003915302,0.00001849655,0.8417249,0.002194185,0.1539668,0.001843903,0.00001132048],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01265077,0.0003487107,0.979784,0.0003514362,0.00007743177,0.00004045105,0.00009074456,0.001498509,0.005157823],"genre_scores_gemma":[0.8552926,0.0005545216,0.1357596,0.0003235184,0.00008922978,0.0001582275,0.000182575,0.0004510336,0.007188828],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006515888,"threshold_uncertainty_score":0.02179784,"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."}}