{"id":"W1504915502","doi":"10.1609/aaai.v24i1.7751","title":"Using Bisimulation for Policy Transfer in MDPs","year":2010,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Office of Naval Research; Natural Sciences and Engineering Research Council of Canada","keywords":"Bisimulation; Computer science; Pessimism; Task (project management); Metric (unit); Markov decision process; Transfer (computing); Action (physics); Quality (philosophy); Theoretical computer science; Artificial intelligence; Markov process; Mathematics; Economics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000500335,0.0001619753,0.00018517,0.000263923,0.0001281397,0.000198497,0.001379483,0.0001074507,0.00001359263],"category_scores_gemma":[0.0006273888,0.0001314968,0.00009246519,0.0007690908,0.0001578598,0.0004494347,0.0001323076,0.0003377634,0.00001117889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004839562,"about_ca_system_score_gemma":0.0001628805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009045949,"about_ca_topic_score_gemma":0.0000252823,"domain_scores_codex":[0.9985166,0.00000851062,0.0004912039,0.0003320576,0.0003311961,0.0003204646],"domain_scores_gemma":[0.9990047,0.0001129292,0.0001565868,0.0002445915,0.000426884,0.00005430568],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002356649,0.00003470944,0.0003557908,0.00002269453,0.00000349218,5.961643e-8,0.0007024275,0.03153957,0.1277718,0.8285788,0.000003235098,0.01096394],"study_design_scores_gemma":[0.00003171389,0.00008502901,0.0001678421,0.00006005424,0.000003444142,0.000001116849,0.0000422446,0.6853062,0.2513439,0.06279636,0.00004702085,0.0001150915],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2663267,0.000001280397,0.7284734,0.002025372,0.0004069174,0.000529301,0.000001337174,0.00004787216,0.002187859],"genre_scores_gemma":[0.9842435,0.000003425959,0.01543394,0.0001233703,0.00009056441,0.00001474096,2.785011e-7,0.00001133003,0.0000788914],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7657824,"threshold_uncertainty_score":0.5362282,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.135113029198047,"score_gpt":0.3565051551249854,"score_spread":0.2213921259269385,"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."}}