{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002248397,0.001259544,0.001512012,0.0004142707,0.0005171467,0.0007906103,0.002266118,0.00111434,0.0009545653],"category_scores_gemma":[0.008882414,0.0006982224,0.0005634014,0.000312103,0.0014364,0.001527872,0.001890871,0.001781806,0.0001583532],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000967079,"about_ca_system_score_gemma":0.001174933,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004360452,"about_ca_topic_score_gemma":0.003835073,"domain_scores_codex":[0.9989321,0.0003295726,0.00006793744,0.0002122414,0.0002730663,0.0001850168],"domain_scores_gemma":[0.9952126,0.003118532,0.0005191888,0.0004227638,0.0004948802,0.0002321617],"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":[0.0001982869,0.0001193137,0.001434735,0.00008135359,0.00008461379,0.0001668854,0.0001486472,0.9484289,0.002505792,0.004611129,0.0006728139,0.04154747],"study_design_scores_gemma":[0.00001607036,0.00004292987,0.00009251088,0.000003249387,0.000006504265,0.00001325133,0.000007237414,0.9958183,0.0006168184,0.003258914,0.0001190453,0.000005146171],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1371126,0.0005438263,0.8576794,0.0003903017,0.00008661456,0.00009893882,0.00004180968,0.001604341,0.002442207],"genre_scores_gemma":[0.9692665,0.0000690559,0.02944301,0.0001777964,0.00002820823,0.00009704872,0.00003483915,0.0000527532,0.0008307943],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004360452,"threshold_uncertainty_score":0.01189077,"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."}}