{"id":"W4240203305","doi":"10.22215/etd/2014-10293","title":"Multiple Model Reinforcement Learning for Environments with Poissonian Time Delays","year":2014,"lang":"en","type":"dissertation","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"","keywords":"Reinforcement learning; Computer science; Convergence (economics); Mobile robot; Robot; Reinforcement; Q-learning; Artificial intelligence; Grid; Simulation; Mathematics; Engineering","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":[0.0003160429,0.0005052012,0.0004382838,0.0002000025,0.0003450473,0.0002576632,0.001127916,0.0002917877,0.00005600408],"category_scores_gemma":[0.00008767923,0.0004427239,0.0001468514,0.0001266372,0.00002397464,0.000377985,0.0001211587,0.0004336042,0.0003500898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001880793,"about_ca_system_score_gemma":0.0001275693,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002343872,"about_ca_topic_score_gemma":0.00001800775,"domain_scores_codex":[0.9973291,0.00004008797,0.0005165242,0.00075049,0.0007442979,0.0006194594],"domain_scores_gemma":[0.9982661,0.0001563706,0.0005484198,0.0007828857,0.00008162297,0.0001646239],"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":[0.00005744031,0.0000140823,0.00007356589,0.00007093803,0.0000799604,0.00000113067,0.0005505497,0.9946703,0.0003220136,0.001914256,0.0005080788,0.001737623],"study_design_scores_gemma":[0.0009135022,0.0005116458,0.00007019616,0.00009979404,0.00005026645,0.000001603842,0.00003101508,0.9885686,0.0008625216,0.00005526126,0.008246062,0.0005895252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.0006203023,0.00001131519,0.9750642,0.00004736437,0.0001656837,0.0008969409,6.57946e-7,0.0002313008,0.0229623],"genre_scores_gemma":[0.2712138,0.00002026108,0.1911267,0.0002479045,0.00008114961,0.0002587006,0.001379886,0.0001275221,0.535544],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7839374,"threshold_uncertainty_score":0.9998025,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01021222507287907,"score_gpt":0.2247518188517965,"score_spread":0.2145395937789175,"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."}}