{"id":"W2157544132","doi":"10.48550/arxiv.1207.5554","title":"Bellman Error Based Feature Generation using Random Projections on Sparse Spaces","year":2012,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Reinforcement learning; Bellman equation; Computer science; Logarithm; Dimension (graph theory); Sparse approximation; Contraction (grammar); Representation (politics); Mathematical optimization; Algorithm; Feature (linguistics); Convergence (economics); Mathematics; Artificial intelligence","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":[0.002931492,0.0008167027,0.001380169,0.0006843465,0.0004976827,0.0008426773,0.001378432,0.001067903,0.002257648],"category_scores_gemma":[0.01235738,0.0005553018,0.0007271577,0.0006827657,0.001358531,0.001989584,0.001925577,0.001869868,0.0004630871],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009312889,"about_ca_system_score_gemma":0.001263178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002080973,"about_ca_topic_score_gemma":0.001891598,"domain_scores_codex":[0.9983506,0.000707947,0.00006967017,0.00025931,0.0004652448,0.0001472971],"domain_scores_gemma":[0.9936954,0.004035435,0.0005989361,0.0007822252,0.0007213788,0.0001665952],"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":[0.0002306886,0.0001165813,0.0009343086,0.00009138991,0.00004876127,0.00009593632,0.0001189805,0.8066194,0.003993952,0.04826824,0.001271574,0.1382101],"study_design_scores_gemma":[0.00001196459,0.00003817149,0.00004964419,0.000004773627,0.000002787004,0.00001132412,0.000002820173,0.9898921,0.001034441,0.008762934,0.0001837586,0.000005250269],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009653842,0.00004665667,0.9895009,0.0000774588,0.00001295222,0.00003873751,0.00002285053,0.0002434704,0.0004029862],"genre_scores_gemma":[0.535874,0.00009210579,0.461627,0.000115022,0.00003724822,0.000345243,0.0001628688,0.0001372205,0.001609254],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.002931492,"threshold_uncertainty_score":0.01550341,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03420690341322675,"score_gpt":0.2673350574748708,"score_spread":0.2331281540616441,"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."}}