{"id":"W2982388063","doi":"10.48550/arxiv.1910.13213","title":"Overcoming Catastrophic Interference in Online Reinforcement Learning with Dynamic Self-Organizing Maps","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Data Stream Mining Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Computer science; Generalization; Artificial neural network; Sample (material); Interference (communication); Locality; Artificial intelligence; Independent and identically distributed random variables; Machine learning; Telecommunications; Mathematics; Channel (broadcasting)","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":[0.0002883206,0.0004496427,0.0004578575,0.0005973955,0.00009278113,0.0001866548,0.002920302,0.0002349604,0.00001075853],"category_scores_gemma":[0.00003854802,0.0005003308,0.00007672093,0.000737295,0.00006528262,0.0006880065,0.005245712,0.001453919,0.00004355092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008483604,"about_ca_system_score_gemma":0.0003377259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004786695,"about_ca_topic_score_gemma":0.0002602599,"domain_scores_codex":[0.9975163,0.0001455157,0.0003093593,0.001381691,0.000135777,0.0005113607],"domain_scores_gemma":[0.9975685,0.00009977482,0.0004172419,0.001687767,0.0001147678,0.000111875],"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":[0.00009578832,0.0002655858,0.04762249,0.0003818938,0.0001880875,0.001200213,0.001787465,0.9262056,0.0002386207,0.02018318,0.0001183696,0.001712748],"study_design_scores_gemma":[0.0006559306,0.00032085,0.002081115,0.001247559,0.00005102372,0.00002184812,0.0002378567,0.9925714,0.0001910057,0.001670659,0.0001674876,0.0007832487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.376097,0.00001671954,0.6223704,0.00003745074,0.0001354115,0.0003023335,0.00001753706,0.000609363,0.0004137738],"genre_scores_gemma":[0.9634594,0.0001305243,0.03571407,0.00003728685,0.0000161634,0.000001350246,0.0002088047,0.00003415342,0.0003982819],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5873623,"threshold_uncertainty_score":0.9997448,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0343324705594077,"score_gpt":0.1915805086300933,"score_spread":0.1572480380706857,"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."}}