{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002885076,0.0002803285,0.0002927725,0.0001884447,0.0003908596,0.0002891277,0.003077641,0.000248857,0.00003687152],"category_scores_gemma":[0.00006088208,0.0003383401,0.0001911531,0.0001112092,0.00006313651,0.0004379611,0.004365674,0.0007916834,0.0001589274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002126552,"about_ca_system_score_gemma":0.0001612258,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000225543,"about_ca_topic_score_gemma":0.0000367256,"domain_scores_codex":[0.9981193,0.00007995236,0.0001873195,0.001093422,0.0001214065,0.0003986082],"domain_scores_gemma":[0.9971732,0.00003654485,0.0003837201,0.002128737,0.000115271,0.0001625179],"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":[0.000004387911,0.00001094048,0.000890397,0.00003390535,0.00003755399,0.0001346446,0.000257067,0.8722845,0.000005064067,0.1246091,0.00002464821,0.001707793],"study_design_scores_gemma":[0.0002637907,0.00002708507,0.000174282,0.00008472472,0.0000247405,0.000003210679,0.0000292586,0.9795123,0.00003036193,0.01825406,0.001243278,0.0003528635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02071871,0.00006452914,0.9630174,0.0001059002,0.0007408502,0.0001994544,2.264262e-7,0.0002933809,0.01485953],"genre_scores_gemma":[0.9885516,0.0001523989,0.003209362,0.00006375921,0.000120036,9.965856e-7,0.00000567022,0.00001428551,0.007881902],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9678329,"threshold_uncertainty_score":0.9999068,"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."}}