{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008672715,0.000363711,0.0002991121,0.0005693244,0.0006104972,0.0004725306,0.0007005818,0.0002803114,0.00001565756],"category_scores_gemma":[0.0002053662,0.0003473325,0.0001680096,0.0008255893,0.00005964483,0.001051978,0.0001902156,0.0005427556,0.00003287464],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005215196,"about_ca_system_score_gemma":0.0002373556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009593404,"about_ca_topic_score_gemma":0.0002076844,"domain_scores_codex":[0.9975196,0.0002550454,0.0003465741,0.000446801,0.0005648201,0.0008671949],"domain_scores_gemma":[0.998054,0.0001213105,0.0002962991,0.0011034,0.0001188869,0.000306152],"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":[0.00004159927,0.0001821891,0.01109663,0.00001813451,0.00003357215,0.000009378728,0.000390941,0.9509068,0.01281698,0.01890079,0.003883208,0.001719751],"study_design_scores_gemma":[0.0007319198,0.0001417315,0.002877176,0.00004163665,0.00002940022,0.00004093179,0.00002702588,0.9748582,0.01678564,0.00005109975,0.00403326,0.0003819879],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03116245,0.0002399548,0.962495,0.003122819,0.000585628,0.0008908873,0.00000454453,0.0008384292,0.0006602691],"genre_scores_gemma":[0.657027,0.00001238933,0.3397406,0.001647472,0.0003896601,0.0001470218,0.0000198846,0.00004147752,0.0009744765],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6258646,"threshold_uncertainty_score":0.9998979,"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."}}