{"id":"W4318620677","doi":"10.48550/arxiv.2301.11490","title":"Neural Episodic Control with State Abstraction","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"JST-Mirai Program; Japan Society for the Promotion of Science; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Abstraction; Computer science; Leverage (statistics); Episodic memory; Reinforcement learning; Artificial intelligence; Sample (material); State (computer science); Inefficiency; Control (management); Machine learning; Scalability; Programming language; Psychology; Database","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008480549,0.0006841857,0.0006867131,0.0003030569,0.000251326,0.0006846135,0.001317012,0.0005269184,0.002326926],"category_scores_gemma":[0.002533544,0.000285111,0.0003996729,0.0003048204,0.000859375,0.001026448,0.001226207,0.001161387,0.0003040852],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006794322,"about_ca_system_score_gemma":0.0009091552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004110607,"about_ca_topic_score_gemma":0.004684545,"domain_scores_codex":[0.9996042,0.00008004065,0.00002828044,0.0001252644,0.0001034824,0.00005893475],"domain_scores_gemma":[0.9991817,0.0003347619,0.0001106837,0.0001858957,0.0001328159,0.00005417901],"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":[0.0001411474,0.0001046808,0.001143245,0.00009042494,0.00005069749,0.00006124535,0.00007730134,0.8169487,0.004447199,0.01229296,0.001566563,0.1630758],"study_design_scores_gemma":[0.000009389027,0.00002797237,0.00008938432,0.000003771836,0.000004996395,0.000008499818,0.000002891099,0.9954052,0.0007563432,0.003357572,0.0003305305,0.000003488518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03230757,0.0002734105,0.962805,0.0001332137,0.00005378374,0.0000614137,0.00007616057,0.001344225,0.002945175],"genre_scores_gemma":[0.9189457,0.0001178441,0.07816105,0.0001289354,0.00003075858,0.0001222967,0.0001589203,0.00006274995,0.002271715],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004110607,"threshold_uncertainty_score":0.008173347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07064646825082561,"score_gpt":0.1866594901952144,"score_spread":0.1160130219443888,"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."}}