{"id":"W2160538589","doi":"","title":"Manifold Embeddings for Model-Based Reinforcement Learning under Partial Observability","year":2009,"lang":"en","type":"article","venue":"","topic":"Neural dynamics and brain function","field":"Neuroscience","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Observability; Reinforcement learning; Observable; Embedding; Computer science; Context (archaeology); Manifold (fluid mechanics); Artificial intelligence; State space; Nonlinear system; Nonlinear dimensionality reduction; Space (punctuation); Mathematics; Applied mathematics; Physics; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001709287,0.0001162737,0.0001046506,0.00003060644,0.0002076944,0.00006430782,0.000111755,0.0000472573,0.00006601377],"category_scores_gemma":[0.000179433,0.00009818135,0.00009434101,0.00009811422,0.0000187167,0.0001555169,0.00001696184,0.0001044793,0.00001211025],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005667765,"about_ca_system_score_gemma":0.00002795054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005166761,"about_ca_topic_score_gemma":0.000002151972,"domain_scores_codex":[0.9989671,0.00002607832,0.0001947507,0.0003579234,0.0001846043,0.0002695373],"domain_scores_gemma":[0.9995531,0.0001213613,0.0000609113,0.0001649093,0.00003268156,0.00006699372],"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":[0.0000885129,0.00004094233,0.0000397247,0.000007556383,6.869777e-7,5.239709e-7,0.00001220952,0.7094499,0.2157335,0.07341531,0.0001959644,0.001015156],"study_design_scores_gemma":[0.0003800445,0.0003065011,0.0001643409,0.000003689747,0.000005490293,6.342871e-7,0.000007091034,0.9024928,0.08919472,0.006539222,0.0007857661,0.0001197061],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3972847,9.280971e-7,0.5960004,0.002343702,0.0001571222,0.0004145012,0.000001582499,0.0001843832,0.003612673],"genre_scores_gemma":[0.9882933,0.000001245313,0.0008225296,0.006701932,0.00004060577,0.00001999166,0.000006389852,0.000008890215,0.004105083],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5951779,"threshold_uncertainty_score":0.4003719,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05870984771643132,"score_gpt":0.2902077674493092,"score_spread":0.2314979197328778,"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."}}