{"id":"W2751124354","doi":"10.48550/arxiv.1709.02349","title":"A Deep Reinforcement Learning Chatbot","year":2017,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":200,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Chatbot; Reinforcement learning; Computer science; Artificial intelligence; Artificial neural network; Deep learning; Machine learning; Sequence (biology); Ensemble learning; Natural language processing","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001123386,0.0008274193,0.0007279793,0.0003626755,0.0006424219,0.0005947497,0.002137072,0.001377978,0.007961829],"category_scores_gemma":[0.003768764,0.0003447284,0.0003941888,0.0002394724,0.0006419913,0.001349897,0.001664708,0.001645095,0.002060717],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006977979,"about_ca_system_score_gemma":0.0009358458,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003351997,"about_ca_topic_score_gemma":0.003473142,"domain_scores_codex":[0.9994338,0.000202532,0.00002297647,0.0001522885,0.000114038,0.00007435615],"domain_scores_gemma":[0.9988648,0.0005629085,0.00006340328,0.0001324824,0.0001726018,0.0002038617],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002797426,0.00289724,0.007236251,0.001102848,0.0003685117,0.001475614,0.001023076,0.361621,0.05774812,0.04061037,0.06444249,0.458677],"study_design_scores_gemma":[0.0001396633,0.0002838187,0.0003742671,0.00002387071,0.00002445789,0.0001363599,0.00003456541,0.9758279,0.005902863,0.008834259,0.008387657,0.00003037214],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1196214,0.001271718,0.8264681,0.00161927,0.0008254569,0.0006420835,0.0009174827,0.03131253,0.01732202],"genre_scores_gemma":[0.7571524,0.0001773167,0.2181733,0.0009259963,0.0001093346,0.0005670844,0.001089718,0.0004376997,0.02136709],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.007961829,"threshold_uncertainty_score":0.02663499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09029315580694751,"score_gpt":0.197397113452557,"score_spread":0.1071039576456095,"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."}}