{"id":"W2407441816","doi":"","title":"Reinforcement Learning with Limited Reinforcement: Using Bayes Risk for Active Learning in POMDPs.","year":2008,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Partially observable Markov decision process; Reinforcement learning; Computer science; Planner; Markov decision process; Artificial intelligence; Automated planning and scheduling; Machine learning; Bayesian probability; Domain (mathematical analysis); Markov process; Markov chain; Markov model; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006468582,0.0004504673,0.000461519,0.0005681796,0.0009268043,0.0001857899,0.0008143341,0.0001540174,0.00005637513],"category_scores_gemma":[0.0003922782,0.0004010421,0.0001343099,0.001030133,0.0000984135,0.001386082,0.0003945594,0.0008761111,0.00003255242],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004244475,"about_ca_system_score_gemma":0.0002894328,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002864045,"about_ca_topic_score_gemma":0.00001459416,"domain_scores_codex":[0.9965789,0.000177654,0.0007383585,0.000744827,0.0007660514,0.0009942356],"domain_scores_gemma":[0.9978518,0.0004609108,0.0006431661,0.0005862695,0.0002762021,0.0001816514],"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":[0.0001077334,0.00002563219,0.01189228,0.00002896439,0.00008849469,0.00002332079,0.003339056,0.9799072,0.0001495037,0.002922009,0.00003685307,0.001478985],"study_design_scores_gemma":[0.002373264,0.001202841,0.001665305,0.0001006594,0.00002926008,0.00004332736,0.0004051139,0.9875909,0.001780957,0.0000287001,0.004207482,0.0005721557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04351272,0.00002290887,0.9464915,0.00008232318,0.0001268273,0.0009000142,2.46171e-7,0.0006372234,0.008226237],"genre_scores_gemma":[0.8723774,0.0001411458,0.1224643,0.0001565315,0.00006323873,0.00006779461,0.00002092824,0.00005091591,0.004657749],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8288646,"threshold_uncertainty_score":0.9998441,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02959896535382437,"score_gpt":0.2529070386760443,"score_spread":0.2233080733222199,"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."}}