{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0007068662,0.0004838884,0.0004996108,0.000758904,0.0002792307,0.0003215382,0.002274054,0.0003534264,0.0001326669],"category_scores_gemma":[0.0002322495,0.000630109,0.0002415098,0.0009724073,0.00009578285,0.0007904587,0.004509557,0.002305273,0.0005219895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007728848,"about_ca_system_score_gemma":0.0002882465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005061512,"about_ca_topic_score_gemma":0.00006164165,"domain_scores_codex":[0.9964746,0.0004558622,0.0005741652,0.001460938,0.0003219294,0.0007124559],"domain_scores_gemma":[0.9972525,0.0002510064,0.0007034374,0.001436677,0.0001764314,0.0001800115],"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":[0.00002024262,0.00003039545,0.05136216,0.00007473503,0.0000744944,0.0001827201,0.0009842878,0.9279716,0.00003543781,0.01904353,0.00004542395,0.000174947],"study_design_scores_gemma":[0.0008743195,0.0001637578,0.003471173,0.0001873611,0.00004106343,0.000003975534,0.000554679,0.9926748,0.00004554641,0.0006979607,0.0006675469,0.0006178328],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06753138,0.00002401155,0.9078549,0.00006936129,0.0005966644,0.0006389396,3.076976e-7,0.0003614106,0.0229231],"genre_scores_gemma":[0.9798797,0.0002693601,0.002854385,0.00008504728,0.00005220925,0.000003793435,0.00007712847,0.00003943702,0.01673887],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9123484,"threshold_uncertainty_score":0.9999964,"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."}}