{"id":"W4389650673","doi":"10.48550/arxiv.2312.05822","title":"Toward Open-ended Embodied Tasks Solving","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Microsoft Research","keywords":"Embodied cognition; Task (project management); Computer science; Robot; Human–computer interaction; Artificial intelligence; Control (management); State (computer science); Plan (archaeology); Engineering","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"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":[0.001193248,0.0006596046,0.000465135,0.0002431032,0.0003894188,0.001068078,0.001138195,0.001217651,0.001634959],"category_scores_gemma":[0.003799071,0.0003451831,0.0005475474,0.0002007885,0.001914086,0.001854252,0.00313426,0.002075151,0.0002952675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006255055,"about_ca_system_score_gemma":0.0008105407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001420917,"about_ca_topic_score_gemma":0.00175349,"domain_scores_codex":[0.9994428,0.0002369412,0.00002779007,0.000108582,0.0001349527,0.00004892066],"domain_scores_gemma":[0.99878,0.0007518661,0.0001095613,0.0001458107,0.0001005452,0.0001123042],"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":[0.0001196088,0.0002122792,0.001214497,0.0002667669,0.0000504984,0.000175616,0.001815517,0.6963977,0.0198323,0.1536111,0.001563893,0.1247401],"study_design_scores_gemma":[0.00003280819,0.00006546283,0.000135263,0.00002422619,0.000008128227,0.00003485316,0.000125174,0.8921994,0.003645634,0.1001443,0.003573117,0.00001161562],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04031616,0.000197973,0.9540477,0.0004026528,0.00002003912,0.00005497633,0.00001968169,0.0004364132,0.004504372],"genre_scores_gemma":[0.6236738,0.0002897148,0.3717571,0.0001440787,0.00001667201,0.0001644263,0.00007766831,0.0001114863,0.003765058],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001634959,"threshold_uncertainty_score":0.006310642,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1926690095202335,"score_gpt":0.2343394282668352,"score_spread":0.04167041874660163,"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."}}