{"id":"W2133552775","doi":"","title":"Learning from Limited Demonstrations","year":2013,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":72,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Variety (cybernetics); Task (project management); Key (lock); Path (computing); Artificial intelligence; Machine learning; Mathematical optimization; Temporal difference learning; Mathematics","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":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001459124,0.0001446198,0.0001391362,0.0001593278,0.0003889188,0.002683664,0.0005030924,0.00008430407,0.00002014377],"category_scores_gemma":[0.0001226523,0.000130721,0.00003507361,0.0004300872,0.00002839782,0.009905141,0.00009446697,0.0002692464,0.0008233899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004886328,"about_ca_system_score_gemma":0.00006543627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001814177,"about_ca_topic_score_gemma":4.550466e-7,"domain_scores_codex":[0.9985517,0.00007156991,0.0005813006,0.0001402922,0.0004013169,0.000253846],"domain_scores_gemma":[0.9988053,0.00007767429,0.0004257515,0.0002544578,0.0003456596,0.00009114947],"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":[6.565448e-7,0.000004662277,0.001427216,0.00006763845,0.000007914984,4.025693e-7,0.00217378,0.9477512,0.0002316718,0.001235438,0.001628859,0.04547051],"study_design_scores_gemma":[0.0001566945,0.00004010701,0.00159925,0.00005535943,0.000003313193,0.000009655053,0.0003865198,0.9919913,0.00009237239,0.00003448457,0.005478017,0.0001528784],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01333712,0.0000697689,0.9760004,0.0004689774,0.0005264495,0.0003285171,4.76155e-7,0.0007110412,0.008557254],"genre_scores_gemma":[0.9931545,0.000003623521,0.005782755,0.0002948731,0.00007321599,0.00006198107,0.00004926847,0.000006655679,0.0005730748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9798175,"threshold_uncertainty_score":0.9999546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01983794697850236,"score_gpt":0.2250760590633588,"score_spread":0.2052381120848564,"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."}}