{"id":"W2575899338","doi":"10.1609/aaai.v31i1.10911","title":"Policy Search with High-Dimensional Context Variables","year":2017,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Japan Society for the Promotion of Science; Deutsche Forschungsgemeinschaft","keywords":"Dimensionality reduction; Principal component analysis; Computer science; Machine learning; Artificial intelligence; Curse of dimensionality; Context (archaeology); Entropy (arrow of time); Pattern recognition (psychology)","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":[0.0007019489,0.0002010452,0.0002358775,0.0001413031,0.0009840993,0.0008361246,0.002843367,0.00007197766,0.00007756378],"category_scores_gemma":[0.0007010549,0.000136605,0.00006711851,0.0003016524,0.0005572603,0.0006945254,0.0005709074,0.0003980504,0.0001255101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004172287,"about_ca_system_score_gemma":0.0003183302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004423105,"about_ca_topic_score_gemma":0.00002628661,"domain_scores_codex":[0.9981148,0.00002696006,0.000337842,0.0004685072,0.0006773585,0.0003745464],"domain_scores_gemma":[0.9979866,0.0001145694,0.0004236551,0.0005368408,0.0008120526,0.0001262668],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006838905,0.00006576577,0.0002462498,0.0000125394,0.00001486426,9.276661e-7,0.0008439239,0.0001937955,0.008998481,0.9154179,0.00005373117,0.07408344],"study_design_scores_gemma":[0.0001959774,0.0006080808,0.00481443,0.0005864232,0.00001776953,0.00002458944,0.001270329,0.1577706,0.5049446,0.3287628,0.0004064673,0.0005979409],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6302345,0.00003437971,0.1788789,0.06572531,0.00127796,0.001406667,0.00001632339,0.0003940536,0.1220319],"genre_scores_gemma":[0.990851,0.000008754215,0.007546291,0.0004478192,0.00009113433,0.00001272607,3.320602e-7,0.00001201172,0.001029925],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5866551,"threshold_uncertainty_score":0.8062769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08807321710670347,"score_gpt":0.3139961377912633,"score_spread":0.2259229206845599,"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."}}