{"id":"W2991820108","doi":"10.48550/arxiv.1912.04002","title":"Learning Sparse Representations Incrementally in Deep Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reinforcement learning; Artificial intelligence; Computer science; Machine learning; Cognitive science; 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":[0.001339761,0.000612667,0.0007202445,0.0003033064,0.0002181156,0.0004883191,0.000971877,0.000751711,0.0009385939],"category_scores_gemma":[0.006800365,0.0004386828,0.000270548,0.0002610265,0.001012597,0.001243073,0.001104261,0.00168156,0.0001531908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006260411,"about_ca_system_score_gemma":0.0007812313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002561888,"about_ca_topic_score_gemma":0.003258569,"domain_scores_codex":[0.9995276,0.0001758996,0.00002024902,0.00007494686,0.0001190997,0.00008219991],"domain_scores_gemma":[0.9976525,0.001538141,0.0002483859,0.00020326,0.0002365808,0.0001211653],"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":[0.0001236773,0.0001259074,0.001313395,0.00004743891,0.00003738385,0.00007708979,0.00006362197,0.9458455,0.003629499,0.007598799,0.0006006078,0.0405372],"study_design_scores_gemma":[0.000007652513,0.00002321284,0.00005363881,0.000001938373,0.00000246508,0.000005622305,0.000002632017,0.9962478,0.0004399893,0.003153423,0.00005949859,0.000002108053],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1511472,0.0002116966,0.8457105,0.0004002233,0.00004741029,0.00007576215,0.00004875504,0.0007724953,0.001585879],"genre_scores_gemma":[0.9582301,0.00006369104,0.04071712,0.000102901,0.00001803647,0.00006817027,0.00004819625,0.00002619045,0.0007255975],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002561888,"threshold_uncertainty_score":0.007085443,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0612828309903429,"score_gpt":0.2105553666551409,"score_spread":0.149272535664798,"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."}}