{"id":"W2963742410","doi":"","title":"DOM-Q-NET: Grounded RL on Structured Language","year":2019,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Reinforcement learning; Artificial intelligence; Task (project management); Machine learning; The Internet; String (physics); Graph; Natural language processing; Theoretical computer science; World Wide Web","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":[0.0008564518,0.0008285326,0.0006302873,0.000310902,0.0003884195,0.0008699155,0.001707885,0.001252725,0.004470039],"category_scores_gemma":[0.003292947,0.0005600962,0.0005374503,0.0002719336,0.001049613,0.001587045,0.001563926,0.001836975,0.001125591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009876103,"about_ca_system_score_gemma":0.001257002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00942892,"about_ca_topic_score_gemma":0.01323801,"domain_scores_codex":[0.9997138,0.0001045878,0.00001212883,0.00007521633,0.00005296361,0.00004123606],"domain_scores_gemma":[0.9992791,0.0004417508,0.00003857938,0.00008919383,0.00009337445,0.00005802536],"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":[0.0001300813,0.0000602173,0.0004525937,0.00005113189,0.00002445262,0.00008480411,0.00005772074,0.9347816,0.001922556,0.01453986,0.002216841,0.04567815],"study_design_scores_gemma":[0.000007202314,0.000009002368,0.0000156895,0.000003177802,0.000001482376,0.000003360303,0.000002279301,0.9940783,0.0002829163,0.005336134,0.0002585551,0.000001955925],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01462927,0.0001325756,0.9782696,0.0002601806,0.00006742907,0.00005288583,0.000167738,0.00307079,0.003349597],"genre_scores_gemma":[0.6955812,0.0002048275,0.2944325,0.0005185282,0.00004223977,0.0002695574,0.0006407877,0.0005263494,0.007784131],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00942892,"threshold_uncertainty_score":0.01874804,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02162800985517141,"score_gpt":0.3421921421386386,"score_spread":0.3205641322834673,"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."}}