{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001679105,0.001105417,0.002146579,0.0006936963,0.000625027,0.0008729713,0.00134444,0.001594163,0.002100778],"category_scores_gemma":[0.007160951,0.0006983911,0.0008341547,0.0006700008,0.00118947,0.001868437,0.001667104,0.001691849,0.0004246303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001078041,"about_ca_system_score_gemma":0.001971189,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004714436,"about_ca_topic_score_gemma":0.005380782,"domain_scores_codex":[0.9989375,0.0004528317,0.00005746407,0.0002902111,0.0001508975,0.0001110005],"domain_scores_gemma":[0.9980938,0.00126335,0.0001530598,0.0002142328,0.0001756728,0.0001000554],"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":[0.0001559749,0.0001411837,0.0008240053,0.0001112634,0.00008224053,0.0000978942,0.0001000936,0.9071757,0.001674709,0.01942102,0.001724126,0.06849174],"study_design_scores_gemma":[0.00001415293,0.00002085384,0.00005609281,0.000005189793,0.000006585599,0.00001112507,0.000006205714,0.9936495,0.0002248774,0.005810079,0.000190912,0.000004417468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03664319,0.0007142585,0.9596988,0.0003168738,0.00005698859,0.00007295538,0.00004897493,0.0008058692,0.001642072],"genre_scores_gemma":[0.8094198,0.0003090674,0.1872246,0.0003960934,0.00008655421,0.0002464924,0.0002201017,0.0001904508,0.001906986],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004714436,"threshold_uncertainty_score":0.009373963,"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."}}