{"id":"W84951255","doi":"","title":"Learning subjective representations for planning","year":2005,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta; University of Waterloo","funders":"","keywords":"Embedding; Representation (politics); Computer science; Artificial intelligence; Domain (mathematical analysis); Construct (python library); Action (physics); Domain knowledge; Robot; Sequence (biology); Knowledge representation and reasoning; Machine 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":[],"consensus_categories":[],"category_scores_codex":[0.0001809096,0.00006805036,0.00006907123,0.00007534156,0.0002121031,0.0001329229,0.0003285118,0.00002774619,0.00002194917],"category_scores_gemma":[0.0001937872,0.00006577455,0.0000434976,0.0001654772,0.00001425173,0.0004968646,0.00009753189,0.0001100923,0.00006878489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003701038,"about_ca_system_score_gemma":0.00002722334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005533242,"about_ca_topic_score_gemma":9.643734e-7,"domain_scores_codex":[0.9992828,0.00002460508,0.000141753,0.0002115912,0.0001372508,0.0002019759],"domain_scores_gemma":[0.999339,0.0002673408,0.00006256408,0.0002149337,0.00007382323,0.00004234213],"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":[0.000001648998,0.000004407604,0.002291317,0.000001882042,0.000008447307,4.46969e-7,0.001194864,0.9548796,0.0001187184,0.036193,0.0006666098,0.004639101],"study_design_scores_gemma":[0.0002186096,0.00008155797,0.001540257,0.000005424585,0.000002670366,0.000003319093,0.0001456562,0.97587,0.001466212,0.0002840222,0.02028485,0.00009743783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001472712,0.00001121587,0.9555637,0.0007694191,0.00009746847,0.0001542152,8.502141e-8,0.0002945279,0.04163671],"genre_scores_gemma":[0.6496452,0.000001238535,0.3358744,0.000217556,0.0001007272,0.00002506017,0.000002952046,0.000006904588,0.01412595],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6481725,"threshold_uncertainty_score":0.2682208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02995310586468893,"score_gpt":0.3183126130565277,"score_spread":0.2883595071918388,"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."}}