{"id":"W7124174011","doi":"10.65109/zzer3937","title":"Using bisimulation for policy transfer in MDPs","year":2010,"lang":"","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Markov process; Work (physics); Bisimulation; Transfer (computing); Partially observable Markov decision process","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":[0.0006052939,0.0002366768,0.000238363,0.0005508984,0.0001746571,0.0003824293,0.0006723026,0.0002441503,0.000101737],"category_scores_gemma":[0.0002354678,0.0002463349,0.0001246106,0.0009692607,0.0000897334,0.0008575867,0.0001056227,0.000427733,0.00002933674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001119827,"about_ca_system_score_gemma":0.0004761103,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005006209,"about_ca_topic_score_gemma":0.000144659,"domain_scores_codex":[0.9979045,0.00004878363,0.0006152273,0.0004759301,0.000330954,0.0006245932],"domain_scores_gemma":[0.998835,0.0002206119,0.00006610185,0.0005987551,0.0001536418,0.0001258925],"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":[0.00001084946,0.00002861001,0.001428357,0.00003180176,0.000007214819,8.878719e-7,0.0007792672,0.8247848,0.007016806,0.1562654,0.000006887024,0.009639118],"study_design_scores_gemma":[0.00102742,0.0001492603,0.001480308,0.0000302634,0.000009664931,0.000003961657,0.000009647577,0.9920294,0.002336094,0.001009142,0.001625536,0.0002893211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0717522,0.000005278508,0.9226857,0.001205648,0.001205465,0.0007054514,0.000001069208,0.00005702179,0.002382195],"genre_scores_gemma":[0.8788232,0.000004659782,0.1194383,0.0003402731,0.0003482382,0.000005770136,0.000002080062,0.00002171318,0.00101582],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.807071,"threshold_uncertainty_score":0.9999989,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06793892293769213,"score_gpt":0.355023856049797,"score_spread":0.2870849331121049,"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."}}