{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002085638,0.00126483,0.001210893,0.000494055,0.0004321709,0.0009060472,0.0009875633,0.001126982,0.002348595],"category_scores_gemma":[0.0109108,0.000515924,0.0006790193,0.0003450734,0.001463481,0.001956088,0.001644385,0.002202592,0.0002681158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001256548,"about_ca_system_score_gemma":0.001012947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003502703,"about_ca_topic_score_gemma":0.002446665,"domain_scores_codex":[0.9992582,0.0003838812,0.00004708579,0.000143106,0.0001111888,0.00005654855],"domain_scores_gemma":[0.9953176,0.00320312,0.0005018552,0.0004836814,0.0003408515,0.0001529024],"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":[0.00006083126,0.00003886986,0.0004193636,0.00004774382,0.00003148035,0.0000298733,0.00005405071,0.9627278,0.0006395159,0.02016512,0.000367022,0.01541827],"study_design_scores_gemma":[0.000004804594,0.00002032851,0.00003177469,0.000002606638,0.000001820911,0.000003546039,0.000002129892,0.9899302,0.0001157533,0.009808728,0.00007539786,0.000002922416],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02906132,0.0001936059,0.9684234,0.0003416598,0.00002986487,0.00004582742,0.00008089935,0.0005650026,0.001258365],"genre_scores_gemma":[0.8945488,0.0001463175,0.103554,0.00008122331,0.00003484796,0.0002029697,0.0002036961,0.0001067392,0.001121428],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003502703,"threshold_uncertainty_score":0.01103008,"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."}}