{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008331244,0.0001479804,0.0001639997,0.0002707373,0.0001258184,0.001001448,0.0003209775,0.00008508768,5.734701e-7],"category_scores_gemma":[0.0001106826,0.000134593,0.0000319232,0.0004698251,0.00001653721,0.007610477,0.00005632541,0.0001226392,0.00002914991],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001712731,"about_ca_system_score_gemma":0.0002231528,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004794793,"about_ca_topic_score_gemma":0.000001624753,"domain_scores_codex":[0.9983467,0.00005568737,0.0007149911,0.0001539787,0.0004827299,0.0002458533],"domain_scores_gemma":[0.9987887,0.00003490759,0.0004591681,0.0002315352,0.0004168205,0.00006890287],"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":[0.00001549355,0.000008028811,0.00009126922,0.0003520761,0.000003298295,1.435573e-7,0.002168358,0.9656221,0.00002340597,0.02006149,0.0005758732,0.01107845],"study_design_scores_gemma":[0.0006495622,0.0002045099,0.00009927128,0.00009589385,0.000004690836,0.000005945661,0.001552707,0.9903277,0.00007249552,0.0003016971,0.006537361,0.0001481243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003242032,0.00004749255,0.9921045,0.0003009099,0.0008692886,0.0006164705,0.000001063756,0.0002516831,0.002566533],"genre_scores_gemma":[0.9829067,0.000001375421,0.01631106,0.0002578786,0.0001058448,0.0001853916,0.00006331178,0.000008319791,0.0001601373],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9796646,"threshold_uncertainty_score":0.9656987,"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."}}