{"id":"W2191938486","doi":"","title":"Basis refinement strategies for linear value function approximation in MDPs","year":2015,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Markov decision process; Basis (linear algebra); Computer science; Bellman equation; Bisimulation; Basis function; Mathematical optimization; Function (biology); Value (mathematics); Markov process; Algorithm; Theoretical computer science; Mathematics; Machine learning","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":[0.003997158,0.0008676283,0.001414494,0.0009974341,0.000618304,0.001180027,0.001732485,0.001334213,0.002737851],"category_scores_gemma":[0.01359828,0.000559744,0.001022088,0.0009199546,0.001993307,0.002230724,0.002801123,0.002589682,0.0004344501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001872595,"about_ca_system_score_gemma":0.001435933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002577952,"about_ca_topic_score_gemma":0.002156374,"domain_scores_codex":[0.9985229,0.0007016817,0.00007240925,0.000162886,0.0004035988,0.0001365501],"domain_scores_gemma":[0.9955983,0.003263679,0.0002247519,0.0003606706,0.0004046128,0.0001480921],"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":[0.00005438016,0.00004584299,0.0003256291,0.00008990656,0.00003514963,0.00004073294,0.0001276333,0.6509156,0.00119643,0.311306,0.0005792712,0.03528349],"study_design_scores_gemma":[0.000008303163,0.00001999571,0.00002096588,0.00001192461,0.000004121448,0.000005864545,0.000008808714,0.940962,0.0003035649,0.0583292,0.0003208032,0.000004534466],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005500892,0.0001117093,0.9931767,0.00007897606,0.000008082738,0.00002988254,0.0000139005,0.00006507704,0.001014733],"genre_scores_gemma":[0.4805576,0.0005287553,0.5150491,0.0001414998,0.00003530925,0.0005838667,0.0001639569,0.0001493061,0.002790608],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003997158,"threshold_uncertainty_score":0.02113926,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05119097121540838,"score_gpt":0.2817875639405395,"score_spread":0.2305965927251311,"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."}}