{"id":"W2182573229","doi":"10.1609/aaai.v29i1.9701","title":"Representation Discovery for MDPs Using Bisimulation Metrics","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Bisimulation; Metric (unit); Computer science; Representation (politics); Computation; Convergence (economics); Markov decision process; Sequence (biology); Theoretical computer science; State space; State (computer science); Metric space; Algorithm; Markov process; Mathematics; Discrete 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":[0.00249747,0.001363434,0.001355622,0.002048339,0.0008006251,0.001750576,0.002011114,0.001278282,0.002889337],"category_scores_gemma":[0.01414871,0.0008458691,0.001837396,0.001321448,0.001420147,0.003278455,0.003721919,0.002188527,0.0006628627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002071491,"about_ca_system_score_gemma":0.00265392,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00426104,"about_ca_topic_score_gemma":0.004242897,"domain_scores_codex":[0.9978185,0.0007096104,0.0001675499,0.0004009934,0.0007582337,0.000145138],"domain_scores_gemma":[0.9954504,0.002759656,0.00045097,0.000633503,0.00057413,0.0001313674],"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":[0.00007095638,0.00006233696,0.0006973746,0.0001752864,0.00005075591,0.00008662317,0.0002085743,0.7584973,0.002792088,0.1162848,0.0009476988,0.1201261],"study_design_scores_gemma":[0.000008481366,0.00002215785,0.00003078541,0.00001457917,0.000005316749,0.00001620347,0.00001628748,0.9647441,0.001036028,0.03329813,0.0008009404,0.000007037444],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004125882,0.00004203897,0.9948522,0.00005614967,0.00000708661,0.00005744133,0.00004160669,0.0002871919,0.0005303305],"genre_scores_gemma":[0.1681065,0.0001350448,0.8300076,0.00005649793,0.00001466087,0.0004263098,0.0003721476,0.0001986909,0.0006826429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00426104,"threshold_uncertainty_score":0.01502973,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2968937454532417,"score_gpt":0.3783388141811964,"score_spread":0.0814450687279547,"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."}}