{"id":"W1555338578","doi":"10.5555/1838206.1838401","title":"Using bisimulation for policy transfer in MDPs","year":2010,"lang":"en","type":"article","venue":"Adaptive Agents and Multi-Agents Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Computer science; Bisimulation; Artificial intelligence; Markov process; Work (physics); Theoretical computer science; Mathematics","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":[0.004637215,0.002022827,0.002214516,0.00130443,0.0008901631,0.00172718,0.002062066,0.002283677,0.007484165],"category_scores_gemma":[0.01857434,0.001103491,0.001503244,0.00103028,0.00263785,0.003376481,0.004161487,0.003420376,0.001074093],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00242865,"about_ca_system_score_gemma":0.00251479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004545149,"about_ca_topic_score_gemma":0.003333232,"domain_scores_codex":[0.9977486,0.001232463,0.0001433554,0.0003582244,0.0003483729,0.0001690841],"domain_scores_gemma":[0.9905217,0.007532929,0.0006161057,0.0005394231,0.0005071627,0.0002827001],"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":[0.00004522041,0.00003319702,0.0001539274,0.00007328436,0.00003215767,0.00003941931,0.00005855825,0.9152627,0.0002838707,0.07266043,0.0003094513,0.01104777],"study_design_scores_gemma":[0.00001642034,0.00002177638,0.00001312821,0.00001327908,0.000005537146,0.000006381877,0.000005846568,0.9485861,0.0001748663,0.05065836,0.0004915995,0.000006607104],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007041451,0.00021767,0.988479,0.0002509709,0.00004409962,0.00007835201,0.00005572907,0.0002901336,0.003542606],"genre_scores_gemma":[0.6509995,0.0008191057,0.3404536,0.0004276528,0.0001078186,0.001340536,0.0003317142,0.0004451838,0.005074942],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007484165,"threshold_uncertainty_score":0.02503705,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1285799627275599,"score_gpt":0.3554582096881,"score_spread":0.2268782469605402,"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."}}