{"id":"W2949600864","doi":"","title":"Model-Based Bayesian Reinforcement Learning in Large Structured Domains","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Computer science; Scalability; Artificial intelligence; Bayesian probability; Machine learning; Bayesian inference","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002037372,0.0008687485,0.001579122,0.0005259342,0.0004623217,0.001053495,0.001463856,0.001457746,0.002246063],"category_scores_gemma":[0.009520848,0.0007454686,0.0005740719,0.0006520157,0.001899613,0.002560781,0.001845715,0.002366775,0.0002847901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00153163,"about_ca_system_score_gemma":0.001182724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007238233,"about_ca_topic_score_gemma":0.006503314,"domain_scores_codex":[0.9990515,0.0004931046,0.00003791559,0.0001622075,0.0001692035,0.00008604497],"domain_scores_gemma":[0.9959702,0.003020043,0.0003192461,0.000253745,0.0002511675,0.0001856314],"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":[0.00004971763,0.00002712172,0.0002799471,0.00005028973,0.00002093204,0.00005409665,0.00005077676,0.9408595,0.0003956544,0.04468511,0.0005336819,0.01299322],"study_design_scores_gemma":[0.00001121406,0.00001028523,0.00003554371,0.000004615818,0.000002298553,0.000005758543,0.000003810868,0.9646465,0.00007469152,0.03504093,0.0001608445,0.000003503732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01797763,0.0003029584,0.9792652,0.0004098079,0.00002245359,0.00002938291,0.00005852669,0.0002721058,0.001661966],"genre_scores_gemma":[0.8405901,0.0004912909,0.1560366,0.0001653425,0.00006730782,0.0001796971,0.000156272,0.00008196984,0.002231455],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007238233,"threshold_uncertainty_score":0.0143922,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04617089644699002,"score_gpt":0.2011105485737758,"score_spread":0.1549396521267858,"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."}}