{"id":"W3035992805","doi":"10.1109/icra48506.2021.9560922","title":"LEAF: Latent Exploration Along the Frontier","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; State (computer science); Reachability; Oracle; Robot; Set (abstract data type); Key (lock); Machine learning; Frontier; Task (project management); State space; Theoretical computer science; Algorithm; Mathematics; Geography","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"],"consensus_categories":[],"category_scores_codex":[0.0003824886,0.0002128937,0.0001987869,0.0000571232,0.0001397401,0.001197305,0.001607786,0.0001577378,0.0001095242],"category_scores_gemma":[0.00006235226,0.0001402956,0.0001408668,0.00014834,0.00003282714,0.0004837005,0.002969682,0.0006221343,0.0001250507],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007473109,"about_ca_system_score_gemma":0.0001719406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001337365,"about_ca_topic_score_gemma":0.00003005607,"domain_scores_codex":[0.9983054,0.0001316402,0.0003325663,0.0004934281,0.0005005827,0.0002363724],"domain_scores_gemma":[0.9979674,0.00006214325,0.0001901698,0.001574352,0.0001584114,0.00004757694],"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":[5.346733e-7,0.000008657369,0.0003976817,0.00001959423,0.00004195247,0.00000937708,0.001329011,0.9818004,0.00001071168,0.007347567,0.00537915,0.003655389],"study_design_scores_gemma":[0.000081629,0.00001708388,0.001130464,0.00006286087,0.00001479259,0.000003265993,0.0001494813,0.992424,0.000387225,0.0007152383,0.00477146,0.0002424824],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006582754,0.0001920174,0.9841449,0.004758615,0.002659404,0.0002737307,1.848377e-7,0.0002326445,0.00708027],"genre_scores_gemma":[0.7029554,0.0004266969,0.2626959,0.002051422,0.0004315733,0.0001303451,0.00009580461,0.00004106165,0.03117174],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.721449,"threshold_uncertainty_score":0.9998395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04681003592202214,"score_gpt":0.2587525507353164,"score_spread":0.2119425148132943,"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."}}