{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004874342,0.002062394,0.002287303,0.001348276,0.0008813567,0.001750513,0.002140412,0.002323498,0.00769304],"category_scores_gemma":[0.01938165,0.001170708,0.001597127,0.001068592,0.00271467,0.003530942,0.004346014,0.003699783,0.001113444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002547061,"about_ca_system_score_gemma":0.002594399,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004315538,"about_ca_topic_score_gemma":0.003288813,"domain_scores_codex":[0.9975744,0.00132199,0.000151418,0.0003883643,0.0003768169,0.0001869578],"domain_scores_gemma":[0.9895288,0.008418654,0.0006478897,0.0005800743,0.0005226815,0.0003018593],"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":[0.00004722316,0.00003546599,0.0001604827,0.00007680705,0.00003405553,0.0000385117,0.00005932235,0.911576,0.0002911217,0.07577798,0.0003243696,0.01157861],"study_design_scores_gemma":[0.00001646888,0.00002316807,0.0000135895,0.00001429695,0.000005760701,0.0000064128,0.000005943248,0.9414076,0.0001823264,0.05782082,0.000496796,0.00000682613],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.006755833,0.0002246313,0.9889656,0.0002481767,0.00004283823,0.0000727345,0.00005541597,0.0002922745,0.003342406],"genre_scores_gemma":[0.6451007,0.0008741588,0.3458971,0.0004539594,0.0001157727,0.001312427,0.0003522406,0.0004926299,0.005401206],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.00769304,"threshold_uncertainty_score":0.02577835,"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."}}